International Speech Communication Association

IINNTTEERRSSPPEEEECCHH 22000066 aanndd

99thth IInntteerrnnaattiioonnaall CCoonnffeerreennccee oonn SSppookkeenn LLaanngguuaaggee PPrroocceessssiinngg

IINNTTEERRSSPPEEEECCHH 22000066 -- IICCSSLLPP

September 17-21, 2006 Pittsburgh, Pennsylvania, USA

Volume 1 of 5

Printed from e-media with permission by:

Curran Associates, Inc. 57 Morehouse Lane

Red Hook, NY 12571 www.proceedings.com

ISBN: 978-1-60423-449-7

Some format issues inherent in the e-media version may also appear in this print version.

International Speech Communication Association

INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing

TABLE OF CONTENTS

VOLUME I

LANGUAGE MODELING FOR SPOKEN DIALOG SYSTEMS

Robust Interpretation in Dialogue by Combining Confidence Scores with Contextual Features............................................................................................................................ 1

Matthew Purver, Florin Ratiu, Lawrence Cavedon

A Clustering Approach to Semantic Decoding ................................................................................ 5Hui Ye, Steve Young

A Bootstrapping Approach for Developing Language Model of New Spoken Dialogue Systems by Selecting Web Texts...................................................................................... 9

Teruhisa Misu, Tatsuya Kawahara

Phoneme-to-Grapheme Mapping for Spoken Inquiries to the Semantic Web............................ 13Axel Horndasch, Elmar Noth, Anton Batliner, Volker Warnke

Bootstrapping Language Models for Dialogue Systems .............................................................. 17Karl Weilhammer, Matthew N. Stuttle, Steve Young

Question Answering with Discriminative Learning Algorithms................................................... 21Junlan Feng

FEATURE ENHANCEMENT FOR ROBUST ASR

Feature Normalization Using Smoothed Mixture Transformations ............................................. 25Patrick Kenny, Vishwa Gupta, G. Boulianne, Pierre Ouellet, Pierre Dumouchel

Stochastic Vector Mapping-Based Feature Enhancement Using Prior Model and Environment Adaptation for Noisy Speech Recognition.............................................................. 29

Chia-Hsin Hsieh, Chung-Hsien Wu, Jun-Yu Lin

A Framework for Robust MFCC Feature Extraction Using SNR-Dependent Compression of Enhanced Mel Filter Bank Energies ................................................................... 33

Babak Nasersharif, Ahmad Akbari

Coupling Particle Filters with Automatic Speech Recognition for Speech Feature Enhancement..................................................................................................................................... 37

Friedrich Faubel, Matthias Wolfel

Extension and Further Analysis of Higher Order Cepstral Moment Normalization (HOCMN) for Robust Features in Speech Recognition................................................................. 41

Chang-Wen Hsu, Lin-Shan Lee

An Improved Mel-Wiener Filter for Mel-LPC Based Speech Recognition ................................... 45Md. Babul Islam, Hiroshi Matsumoto, Kazumasa Yamamoto

DIALOG AND DISCOURSE

A Stochastic Approach for Dialog Management Based on Neural Networks............................. 49Lluis F. Hurtado, David Griol, Encarna Segarra, Emilio Sanchis

Discourse Structure and Speech Recognition Problems ............................................................. 53Mihai Rotaru, Diane J. Litman

A TextTiling Based Approach to Topic Boundary Detection in Meetings .................................. 57Satanjeev Banerjee, Alexander I. Rudnicky

An User-Centered Development of an Intuitive Dialog Control for Speech-Controlled Music Selection in Cars................................................................................................. 61

Stefan Schulz, Hilko Donker

Doing Research on a Deployed Spoken Dialogue System: One Year of Let's Go! Experience ......................................................................................................................................... 65

Antoine Raux, Dan Bohus, Brian Langner, Alan W. Black, Maxine Eskenazi

Detecting Question-Bearing Turns in Spoken Tutorial Dialogues .............................................. 69Jackson Liscombe, Jennifer J. Venditti, Julia Hirschberg

THE SPEECH SEPARATION CHALLENGE

A Computational Auditory Scene Analysis System for Robust Speech Recognition ....................................................................................................................................... 73

Soundararajan Srinivasan, Yang Shao, Zhaozhang Jin, Deliang Wang

CASA Based Speech Separation for Robust Speech Recognition ............................................. 77Runqiang Han, Pei Zhao, Qin Gao, Zhiping Zhang, Hao Wu, Xihong Wu

Enhancement of Harmonic Content of Speech Based on a Dynamic Programming Pitch Tracking Algorithm ................................................................................................................. 81

Mark R. Every, Philip J. B. Jackson

Recent Advances in Speech Fragment Decoding Techniques .................................................... 85Jon Barker, Andre Coy, Ning Ma, Martin Cooke

Speech Recognition Using Factorial Hidden Markov Models for Separation in the Feature Space.................................................................................................................................... 89

Tuomas Virtanen

Combining Missing-Feature Theory, Speech Enhancement and Speaker-Dependent/-Independent Modeling for Speech Separation.......................................................... 93

Ji Ming, Timothy J. Hazen, James R. Glass

Super-Human Multi-Talker Speech Recognition: The IBM 2006 Speech Separation Challenge System ............................................................................................................................. 97

T. Kristjansson, J. Hershey, P. Olsen, S. Rennie, Ramesh Gopinath

Modified Phase Opponency Based Solution to the Speech Separation Challenge................. 101Om D. Deshmukh, Carol Y. Espy-Wilson

MULTILINGUAL AND MULTI-ACCENT PROCESSING

The 2006 RWTH Parliamentary Speeches Transcription System .............................................. 105J. Loof, M. Bisani, Ch. Gollan, G. Heigold, Bjorn Hoffmeister, Ch. Plahl, Ralf Schluter, Hermann Ney

Multilingual Non-Native Speech Recognition Using Phonetic Confusion-Based Acoustic Model Modification and Graphemic Constraints......................................................... 109

G. Bouselmi, D. Fohr, I. Illina, Jean-Paul Haton

Automatic Speech Recognition of Cantonese-English Code-Mixing Utterances .................... 113Joyce Y. C. Chan, P. C. Ching, Tan Lee, Houwei Cao

The ICSI+ Multilingual Sentence Segmentation System............................................................. 117M. Zimmerman, Dilek Hakkani-Tur, J. Fung, N. Mirghafori, L. Gottlieb, Elizabeth Shriberg, Yang Liu

Cross-Language Evaluation of Voice-to-Phoneme Conversions for Voice-Tag Application in Embedded Platforms ............................................................................................. 121

Yan Ming Cheng, Changxue Ma, Lynette Melnar

A Multi-Space Distribution (MSD) Approach to Speech Recognition of Tonal Languages ....................................................................................................................................... 125

Huanliang Wang, Yao Qian, Frank K. Soong, Jian-Lai Zhou, Jiqing Han

Comparison of Acoustic Modeling Techniques for Vietnamese and Khmer ASR ................... 129Viet Bac Le, Laurent Besacier

Multi-Accent Chinese Speech Recognition.................................................................................. 133Yi Liu, Pascale Fung

Comparative Analysis of Formants of British, American and Australian Accents .................. 137Seyed Ghorshi, Saeed Vaseghi, Qin Yan

Automatic Initial/Final Generation for Dialectal Chinese Speech Recognition ........................ 141Linquan Liu, Thomas Fang Zheng, Wenhu Wu

Maximum Entropy Modeling for Diacritization of Arabic Text ................................................... 145Ruhi Sarikaya, Ossama Emam, Imed Zitouni, Yuqing Gao

Comparison of Slovak and Czech Speech Recognition Based on Grapheme and Phoneme Acoustic Models ............................................................................................................ 149

Slavomir Lihan, Jozef Juhar, Anton Cizmar

CORPORA, ANNOTATION, AND ASSESSMENT METRICS I

Integrating Festival and Windows................................................................................................. 153Rhys James Jones, Ambrose Choy, Briony Williams

Measuring the Acceptable Word Error Rate of Machine-Generated Webcast Transcripts....................................................................................................................................... 157

Cosmin Munteanu, Gerald Penn, Ron Baecker, Elaine Toms, David James

Analyzing Reusability of Speech Corpus Based on Statistical Multidimensional Scaling Method................................................................................................................................ 161

Goshu Nagino, Makoto Shozakai

Redundancy and Productivity in the Speech Technology Lexicon --- Can We Do Better?.............................................................................................................................................. 165

Susan Fitt, Korin Richmond

Word Intelligibility Estimation of Noise-Reduced Speech.......................................................... 169Takeshi Yamada, Masakazu Kumakura, Nobuhiko Kitawaki

Exploring the Unknown --- Collecting 1000 Speakers Over the Internet for the Ph@ttSessionz Database of Adolescent Speakers ..................................................................... 173

Christoph Draxler

A New Single-Ended Measure for Assessment of Speech Quality............................................ 177Timothy Murphy, Dorel Picovici, Abdulhussain E. Mahdi

Speech Technology for Minority Languages: The Case of Irish (Gaelic) ................................. 181Ailbhe Ni Chasaide, John Wogan, Brian O Raghallaigh, Aine Ni Bhriain, Eric Zoerner, Harald Berthelsen, Christer Gobl

Further Investigations on the Relationship Between Objective Measures of Speech Quality and Speech Recognition Rates in Noisy Environments.................................. 185

Francisco Jose Fraga, Carlos Alberto Ynoguti, Andre Godoi Chiovato

Non-Intrusive Speech Quality Assessment with Low Computational Complexity .................. 189Volodya Grancharov, David Y. Zhao, Jonas Lindblom, W. Bastiaan Kleijn

Using Speech Recognition Technique for Constructing a Phonetically Transcribed Taiwanese (Min-Nan) Text Corpus .......................................................................... 193

Min-Siong Liang, Ren-Yuan Lyu, Yuang-Chin Chiang

SloParl --- Slovenian Parliamentary Speech and Text Corpus for Large Vocabulary Continuous Speech Recognition .............................................................................. 197

Andrej Zgank, Tomaz Rotovnik, Matej Grasic, Marko Kos, Damjan Vlaj, Zdravko Kacic

An Annotation Scheme for Agreement Analysis ......................................................................... 201Siew Leng Toh, Fan Yang, Peter A. Heeman

SPEECH CODING

Signal Modification Incorporating Perceptual Weighting Filter ................................................. 205Joon-Hyuk Chang, Woohyung Lim, Nam Soo Kim

Enhanced Dynamic Codebook Reordering for Advanced Quantizer Structures ..................... 209Jani Nurminen

An Efficient Segment-Based Speech Compression Technique for Hand-Held TTS Systems ........................................................................................................................................... 213

Chang-Heon Lee, Sung-Kyo Jung, Thomas Eriksson, Won-Suk Jun, Hong-Goo Kang

An Unified Unit-Selection Framework for Ultra Low Bit-Rate Speech Coding ......................... 217Ramasubramanian V., Harish D.

Efficient VQ Techniques and General Noise Shaping in Noise Feedback Coding .................. 221Jes Thyssen, Juin-Hwey Chen

Classified Comfort Noise Generation for Efficient Voice Transmission................................... 225Yasheng Qian, Wei-Shou Hsu, Peter Kabal

Integration of a CELP Coder in the ARDOR Universal Sound Codec ....................................... 229Balazs Kovesi, Dominique Massaloux, David Virette, Julien Bensa

Two Stage Transform Vector Quantization of LSFs for Wideband Speech Coding ................ 233Saikat Chatterjee, T. V. Sreenivas

Comparison of Prediction Based LSF Quantization Methods Using Split VQ ......................... 237Saikat Chatterjee, T. V. Sreenivas

High-Rate Data Embedding in Unvoiced Speech ........................................................................ 241Konrad Hofbauer, Gernot Kubin

Pitch Resynchronization While Recovering from a Late Frame in a Predictive Speech Decoder .............................................................................................................................. 245

Kyle D. Anderson, Philippe Gournay

SPEECH ENHANCEMENT I

A Novel Environment-Dependent Speech Enhancement Method with Optimized Memory Footprint............................................................................................................................ 249

Suhadi Suhadi, Sorel Stan, Tim Fingscheidt

Weighted Codebook Mapping for Noisy Speech Enhancement Using Harmonic-Noise Model ..................................................................................................................................... 253

Esfandiar Zavarehei, Saeed Vaseghi, Qin Yan

MMSE Estimation of Complex-Valued Discrete Fourier Coefficients with Generalized Gamma Priors ............................................................................................................ 257

J. Jensen, R. C. Hendriks, J. S. Erkelens, R. Heusdens

Automatic Removal of Typed Keystrokes from Speech Signals ............................................... 261Amarnag Subramanya, Michael L. Seltzer, Alex Acero

Lattice LP Filtering for Noise Reduction in Speech Signals ...................................................... 265Erhard Rank, Gernot Kubin

Speech Enhancement Using Modified Phase Opponency Model.............................................. 269Om D. Deshmukh, Carol Y. Espy-Wilson

ASR OTHER I

Computer-Assisted Closed-Captioning of Live TV Broadcasts in French ............................... 273G. Boulianne, J.-F. Beaumont, M. Boisvert, J. Brousseau, P. Cardinal, C. Chapdelaine, M. Comeau, Pierre Ouellet, F. Osterrath

On the Use of Morphological Analysis for Dialectal Arabic Speech Recognition ................... 277Mohamed Afify, Ruhi Sarikaya, Hong-Kwang Jeff Kuo, Laurent Besacier, Yuqing Gao

Recognition of Classroom Lectures in European Portuguese .................................................. 281Isabel Trancoso, Ricardo Nunes, Luis Neves, Ceu Viana, Helena Moniz, Diamantino Caseiro, Ana Isabel Mata

Investigating Automatic Decomposition for ASR in Less Represented Languages ............... 285Thomas Pellegrini, Lori Lamel

Automatic Transcription of Somali Language ............................................................................. 289Abdillahi Nimaan, Pascal Nocera, Jean-Francois Bonastre

Analysis of Overlaps in Meetings by Dialog Factors, Hot Spots, Speakers, and Collection Site: Insights for Automatic Speech Recognition..................................................... 293

Ozgur Cetin, Elizabeth Shriberg

MODELING PROSODIC FEATURES

Combining Acoustic, Lexical, and Syntactic Evidence for Automatic Unsupervised Prosody Labeling ................................................................................................... 297

Sankaranarayanan Ananthakrishnan, Shrikanth Narayanan

On the Correlation Between Energy and Pitch Accent in Read English Speech ..................... 301Andrew Rosenberg, Julia Hirschberg

Corpus-Based Generation of Fundamental Frequency Contours Using Generation Process Model and Considering Emotional Focuses ................................................................. 305

Keikichi Hirose, Yasufumi Asano, Nobuaki Minematsu

Prosodic Boundaries in Czech: An Experiment Based on Delexicalized Speech ................... 309Tomas Dubeda

Totally Data-Driven Intonation Prediction Model Using a Novel F0 Contour Parametric Representation ............................................................................................................ 313

Lifu Yi, Jian Li, Xiaoyan Lou, Jie Hao

A Comparison of Inter-Transcriber Reliability for Two Systems of Prosodic Annotation: RaP (Rhythm and Pitch) and ToBI (Tones and Break Indices) ............................. 317

Laura Dilley, Mara Breen, Marti Bolivar, John Kraemer, Edward Gibson

SPOKEN INFORMATION RETRIEVAL

Saliency Parsing for Automated Directory Assistance............................................................... 321Issac Alphonso, Shuangyu Chang

Open-Vocabulary Spoken Document Retrieval Based on New Subword Models and Subword Phonetic Similarity.................................................................................................. 325

Kohei Iwata, Yoshiaki Itoh, Kazunori Kojima, Masaaki Ishigame, Kazuyo Tanaka, Shi-Wook Lee

Improved Topic Classification Over Maximum Entropy Model Using K-Norm Based New Objectives.................................................................................................................... 329

Xiang Li, Ea-Ee Jan, Cheng Wu, David Lubensky

Efficient Interactive Retrieval of Spoken Documents with Key Terms Ranked by Reinforcement Learning................................................................................................................. 333

Yi-Cheng Pan, Jia-Yu Chen, Yen-Shin Lee, Yi-Sheng Fu, Lin-Shan Lee

Discriminative Named Entity Recognition of Speech Data Using Speech Recognition Confidence................................................................................................................. 337

Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki

Using Latent Semantic Indexing for Morph-Based Spoken Document Retrieval .................... 341Ville T. Turunen, Mikko Kurimo

FRONT-END METHODS FOR ASR

Feature Combination Using Linear Discriminant Analysis and Its Pitfalls............................... 345Ralf Schluter, Andras Zolnay, Hermann Ney

Discriminant Linear Processing of Time-Frequency Plane ........................................................ 349Fabio Valente, Hynek Hermansky

Automatic Speech Recognition Experiments with Articulatory Data........................................ 353Esmeralda Uraga, Thomas Hain

Speech Recognition with Phonological Features: Some Issues to Attend .............................. 357Frederik Stouten, Jean-Pierre Martens

Multi-Source Far-Distance Microphone Selection and Combination for Automatic Transcription of Lectures............................................................................................................... 361

Matthias Wolfel, Christian Fugen, Shajith Ikbal, John W. McDonough

Statistical Analysis and Performance of DFT Domain Noise Reduction Filters for Robust Speech Recognition .......................................................................................................... 365

Colin Breithaupt, Rainer Martin

Normalization of the Inter-Frame Information Using Smoothing Filtering ............................... 369L. Garcia, Jose C. Segura, Carmen Benitez, Javier Ramirez, Angel De La Torre

Comparative Study on Contributions of Pitch-Synchronization and Peak-Amplitude Towards Robustness Issue of ASR............................................................................ 373

Muhammad Ghulam, Junsei Horikawa, Tsuneo Nitta

Phoneme Recognition Based on Fisher Weight Map to Higher-Order Local Auto-Correlation ....................................................................................................................................... 377

Yasuo Ariki, Shunsuke Kato, Tetsuya Takiguchi

Data-Driven Design of Front-End Filter Bank for Lombard Speech Recognition .................... 381Hynek Boril, Petr Fousek, Petr Pollak

Optimization of Class Weights for LDA Feature Transformations ............................................ 385Andrej Ljolje

LDA Based Feature Estimation Methods for LVCSR .................................................................. 389Janne Pylkkonen

Robust Feature Extraction Based on Spectral Peaks of Group Delay and Autocorrelation Function and Phase Domain Analysis.............................................................. 393

G. Farahani, S. M. Ahadi, M. Mehdi Homayounpour

Frequency Warping by Linear Transformation of Standard MFCC ........................................... 397Sankaran Panchapagesan

LANGUAGE AND DIALECT RECOGNITION

Automatic Language Identification Using Wavelets ................................................................... 401Ana Lilia Reyes-Herrera, Luis Villasenor-Pineda, Manuel Montes-Y-Gomez

Minimum Classification Error Training of Hidden Markov Models for Acoustic Language Identification.................................................................................................................. 405

Josef G. Bauer, Ekaterina Timoshenko

Unsupervised Adaptation for Acoustic Language Identification............................................... 409Ekaterina Timoshenko, Josef G. Bauer

Low Complexity LID Using Pruned Pattern Tables of LZW ........................................................ 413S. V. Basavaraja, T. V. Sreenivas

Improved Language Identification Using Support Vector Machines for Language Modeling .......................................................................................................................................... 417

Xi Yang, Lu-Feng Zhai, Manhung Siu, Herbert Gish

Recent Advances in Phonotactic Language Recognition Using Binary-Decision Trees................................................................................................................................................. 421

Jiri Navratil

Fusion of Phonotactic and Prosodic Knowledge for Language Identificcation....................... 425Chi-Yueh Lin, Hsiao-Chuan Wang

Vector-Based Spoken Language Recognition Using Output Coding ....................................... 429Haizhou Li, Bin Ma, Rong Tong

Basque-Spanish Language Identification Using Phone-Based Methods ................................. 433Victor G. Guijarrubia, M. Ines Torres

The Role of Prosody in the Perception of US Native English Accents ..................................... 437Ayako Ikeno, John H. L. Hansen

Perceptual Identification and Phonetic Analysis of 6 Foreign Accents in French .................. 441Bianca Vieru-Dimulescu, Philippe Boula De Mareuil

Gaussian Mixture Selection and Data Selection for Unsupervised Spanish Dialect Classification ................................................................................................................................... 445

Rongqing Huang, John H. L. Hansen

SPOKEN DIALOG SYSTEMS I

Dynamic Extension of a Grammar-Based Dialogue System: Constructing an All-Recipes Knowing Robot................................................................................................................. 449

Petra Gieselmann, Alex Waibel

Scalable and Portable Web-Based Multimodal Dialogue Interaction with Geographical Databases ................................................................................................................ 453

Alexander Gruenstein, Stephanie Seneff, Chao Wang

System- versus User-Initiative Dialog Strategy for Driver Information Systems ..................... 457Chantal Ackermann, Marion Libossek

Have We Met? MDP Based Speaker ID for Robot Dialogue........................................................ 461Filip Krsmanovic, Curtis Spencer, Daniel Jurafsky, Andrew Y. Ng

Prominent Words as Anchors for TRP Projection....................................................................... 465R. J. J. H. Van Son, Wieneke Wesseling, Louis C. W. Pols

Learning Multi-Goal Dialogue Strategies Using Reinforcement Learning with Reduced State-Action Spaces ....................................................................................................... 469

Heriberto Cuayahuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira

Pitch Range and Pause Duration as Markers of Discourse Hierarchy: Perception Experiments..................................................................................................................................... 473

Jorg Mayer, Ekaterina Jasinskaja, Ulrike Kolsch

Radiobot-CFF: A Spoken Dialogue System for Military Training .............................................. 477Antonio Roque, Anton Leuski, Vivek Rangarajan, Susan Robinson, Ashish Vaswani, Shrikanth Narayanan, David Traum

Is Voice Quality Enough? --- Study on How the Situation and User's Awareness Influence the Utterance Features .................................................................................................. 481

Shinya Yamada, Toshihiko Itoh, Kenji Araki

Development of Slovak GALAXY/VoiceXML Based Spoken Language Dialogue System to Retrieve Information from the Internet ....................................................................... 485

Jozef Juhar, Stanislav Ondas, Anton Cizmar, Milan Rusko, Gregor Rozinaj, Roman Jarina

LINTest: A Development Tool for Testing Dialogue Systems .................................................... 489Lars Degerstedt, Arne Jonsson

SPEAKER CHARACTERIZATION AND RECOGNITION I

Improving the Characterization of the Alternative Hypothesis via Kernel Discriminant Analysis for Likelihood Ratio-Based Speaker Verification.................................. 493

Yi-Hsiang Chao, Wei-Ho Tsai, Hsin-Min Wang, Ruei-Chuan Chang

A Discriminative Method for Speaker Verification Using the Difference Information ...................................................................................................................................... 497

Zhenchun Lei, Yingchun Yang, Zhaohui Wu

A Multiclass Framework for Speaker Verification Within an Acoustic Event Sequence System ........................................................................................................................... 501

Nicolas Scheffer, Jean-Francois Bonastre

Speaker Cluster Based GMM Tokenization for Speaker Recognition ....................................... 505Bin Ma, Donglai Zhu, Rong Tong, Haizhou Li

Intra-Speaker Variability Compensation in Speaker Verification with Limited Enrolling Data.................................................................................................................................. 509

Claudio Garreton, Nestor Becerra Yoma, Carlos Molina, Fernando Huenupan

Speaking Faces for Face-Voice Speaker Identity Verification ................................................... 513Girija Chetty, Michael Wagner

SYSTEM COMBINATION

A Study on Lattice Rescoring with Knowledge Scores for Automatic Speech Recognition ..................................................................................................................................... 517

Sabato Marco Siniscalchi, Jinyu Li, Chin-Hui Lee

Cross-System Adaptation and Combination for Continuous Speech Recognition: The Influence of Phoneme Set and Acoustic Front-End............................................................. 521

Sebastian Stuker, Christian Fugen, Susanne Burger, Matthias Wolfel

Generating Complementary Systems for Speech Recognition ................................................. 525C. Breslin, M. J. F. Gales

VOLUME II

Investigations of Issues for Using Multiple Acoustic Models to Improve Continuous Speech Recognition .................................................................................................. 529

Rong Zhang, Alexander I. Rudnicky

A New Framework for System Combination Based on Integrated Hypothesis Space................................................................................................................................................ 533

I-Fan Chen, Lin-Shan Lee

Frame Based System Combination and a Comparison with Weighted ROVER and CNC................................................................................................................................................... 537

Bjorn Hoffmeister, Tobias Klein, Ralf Schluter, Hermann Ney

INTERPRETING PROSODIC VARIATION

Towards an Integrated Understanding of Speaking Rate in Conversation .............................. 541Jiahong Yuan, Mark Liberman, Christopher Cieri

Prosody of Interrogative and Affirmative Sentences in Vietnamese Language: Analysis and Perceptive Results................................................................................................... 545

Minh Quang Vprotect Unhbox Voidb@x Penalty @m {}u, Dprotect Unhbox Voidb@x Penalty @m {}o Dat Tran, Eric Castelli

Intonational Cues to Student Questions in Tutoring Dialogs .................................................... 549Jennifer J. Venditti, Julia Hirschberg, Jackson Liscombe

Testing the Effect of Audiovisual Cues to Prominence via a Reaction-Time Experiment....................................................................................................................................... 553

Emiel Krahmer, Marc Swerts

Effect of Genre, Speaker, and Word Class on the Realization of Given and New Information ...................................................................................................................................... 557

Agustin Gravano, Julia Hirschberg

Word Order and Tonal Shape in the Production of Focus in Short Finnish Utterances........................................................................................................................................ 561

Martti Vainio, Juhani Jarvikivi, Stefan Werner

ARTICULATORY MODELING

Modeling Sensory-to-Motor Mappings Using Neural Nets and a 3D Articulatory Speech Synthesizer ........................................................................................................................ 565

Bernd J. Kroger, Peter Birkholz, Jim Kannampuzha, Christiane Neuschaefer-Rube

Semi-Automatic Extraction of Vocal Tract Movements from Cineradiographic Data................................................................................................................................................... 569

Julie Fontecave, Frederic Berthommier

Towards Continuous Speech Recognition Using Surface Electromyography ........................ 573Szu-Chen Jou, Tanja Schultz, Matthias Walliczek, Florian Kraft, Alex Waibel

A Trajectory Mixture Density Network for the Acoustic-Articulatory Inversion Mapping ........................................................................................................................................... 577

Korin Richmond

Articulatory Features for ``Meeting'' Speech Recognition ......................................................... 581Florian Metze

Training of Coarticulation Models Using Dominance Functions and Visual Unit Selection Methods for Audio-Visual Speech Synthesis ............................................................. 585

Zdenek Krnoul, Milos Zelezny, Ludek Muller, Jakub Kanis

ACOUSTIC MODELING I – TRAINING AND TOPOLOGIES

Phone Recognition Analysis for Trajectory HMM ....................................................................... 589Le Zhang, Steve Renals

Discriminative Kernel-Based Phoneme Sequence Recognition ................................................ 593Joseph Keshet, Shai Shalev-Shwartz, Samy Bengio, Yoram Singer, Dan Chazan

Combining Phonetic Attributes Using Conditional Random Fields .......................................... 597Jeremy Morris, Eric Fosler-Lussier

Discriminative MLE Training Using a Product of Gaussian Likelihoods .................................. 601T. Nagarajan, Douglas O'Shaughnessy

State-Level Variable Modeling for Phoneme Classification ....................................................... 605Hao-Zheng Li, Douglas O'Shaughnessy

A Time-Synchronous Phonetic Decoder for a Long-Contextual-Span Hidden Trajectory Model ............................................................................................................................. 609

Xiaolong Li, Li Deng, Dong Yu, Alex Acero

Analysis of HMM Temporal Evolution for Automatic Speech Recognition and Utterance Verification ..................................................................................................................... 613

Marta Casar, Jose A. R. Fonollosa

Improvements to Bucket Box Intersection Algorithm for Fast GMM Computation in Embedded Speech Recognition Systems ................................................................................ 617

Min Tang, Aravind Ganapathiraju

Forward-Backwards Training of Hybrid HMM/BN Acoustic Models .......................................... 621Konstantin Markov, Satoshi Nakamura

A Comparative Study of Gaussian Selection Methods in Large Vocabulary Continuous Speech Recognition .................................................................................................. 625

Dirk Gehrig, Thomas Schaaf

A Successive State and Mixture Splitting for Optimizing the Size of Models in Speech Recognition........................................................................................................................ 629

Soo-Young Suk, Seong-Jun Hahm, Ho-Youl Jung, Hyun-Yeol Chung

Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition........................................................................................................................ 633

Valentin Ion, Reinhold Haeb-Umbach

ACOUSTIC SIGNAL SEGMENTATION AND CLASSIFICATION

Automatic English Stop Consonants Classification Using Wavelet Analysis and Hidden Markov Models ................................................................................................................... 637

Marco Kuhne, Roberto Togneri

Single Frame Selection for Phoneme Classification................................................................... 641Tingyao Wu, Dirk Van Compernolle, Jacques Duchateau, Hugo Van Hamme

On the Relation Between Maximum Spectral Transition Positions and Phone Boundaries ...................................................................................................................................... 645

Sorin Dusan, Lawrence Rabiner

Objective Estimation of Suicidal Risk Using Vocal Output Characteristics............................. 649T. Yingthawornsuk, H. Kaymaz Keskinpala, D. France, D. M. Wilkes, R. G. Shiavi, R. M. Salomon

A Wavelet-Based Parameterization for Speech/Music Segmentation ....................................... 653E. Didiot, I. Illina, O. Mella, D. Fohr, Jean-Paul Haton

Distance Measure Between Gaussian Distributions for Discriminating Speaking Styles................................................................................................................................................ 657

Goshu Nagino, Makoto Shozakai

Bayesian Networks for Phonetic Classification Using Time-Scale Features ........................... 661Franz Pernkopf, Tuan Van Pham

Fast and Effective Retraining on Contrastive Vocal Characteristics with Bidirectional Long Short-Term Memory Nets .............................................................................. 665

Nicole Beringer

Exploiting Dendritic Autocorrelogram Structure to Identify Spectro-Temporal Regions Dominated by a Single Sound Source........................................................................... 669

Ning Ma, Phil Green, Andre Coy

Locating Phone Boundaries from Acoustic Discontinuities Using a Two-Staged Approach ......................................................................................................................................... 673

Pairote Leelaphattarakij, Proadpran Punyabukkana, Atiwong Suchato

Investigation on Rescoring Using Minimum Verification Error (MVE) Detectors .................... 677Qiang Fu, Biing-Hwang Juang

Generalization of the Minimum Classification Error (MCE) Training Based on Maximizing Generalized Posterior Probability (GPP).................................................................. 681

Qiang Fu, Antonio Moreno-Daniel, Biing-Hwang Juang, Jian-Lai Zhou, Frank K. Soong

Unsupervised Detection of Whispered Speech in the Presence of Normal Phonation......................................................................................................................................... 685

Michael A. Carlin, Brett Y. Smolenski, Stanley J. Wenndt

Friends and Enemies: A Novel Initialization for Speaker Diarization ........................................ 689Xavier Anguera, Chuck Wooters, Javier Hernando

LINGUISTICS, PHONOLOGY, AND PHONETICS I

Acoustic Cues for the Classification of Regular and Irregular Phonation................................ 693Kushan Surana, Janet Slifka

Realizations and Representations of Thai Tones in Monomoraic Syllables ............................ 697Rattima Nitisaroj

Measuring and Comparing Vowel Qualities in a Dutch Spontaneous Speech Corpus.............................................................................................................................................. 701

Irene Jacobi, Louis C. W. Pols, Jan Stroop

Phonetic Research on Accented Chinese in Three Dialectal Regions: Shanghai, Wuhan and Xiamen ......................................................................................................................... 705

Aijun Li, Qiang Fang, Ziyu Xiong

Pronunciation Variation Modeling for Mandarin with Accent .................................................... 709Chi Zhang, Ji Wu, Xi Xiao, Zuoying Wang

Specificity and Generalizability of Spontaneous Phonetic Imitation ........................................ 713Kuniko Y. Nielsen

On the Sufficiency of Automatic Phonetic Transcriptions for Pronunciation Variation Research.......................................................................................................................... 717

Christophe Van Bael, Hans Van Halteren

Automatic Detection of Voice Onset Time Contrasts for Use in Pronunciation Assessment ..................................................................................................................................... 721

Abe Kazemzadeh, Joseph Tepperman, Jorge Silva, Hong You, Sungbok Lee, Abeer Alwan, Shrikanth Narayanan

Unfilled Pauses in Japanese Sentences Read Aloud by Non-Native Learners........................ 725Hiroko Hirano, Goh Kawai, Keikichi Hirose, Nobuaki Minematsu

Detection of Quotations and Inserted Clauses and Its Application to Dependency Structure Analysis in Spontaneous Japanese............................................................................. 729

Ryoji Hamabe, Kiyotaka Uchimoto, Tatsuya Kawahara, Hitoshi Isahara

Chinese Input Method Based on Reduced Mandarin Phonetic Alphabet ................................. 733Chun-Han Tseng, Chia-Ping Chen

Thesaurus Expansion Using Similar Word Pairs from Patent Documents............................... 737Yoshimi Suzuki, Fumiyo Fukumoto

Low-Resource Autodiacritization of Abjads for Speech Keyword Search ............................... 741Patrick Schone

SPEECH TRANSLATION

Building an English-Iraqi Arabic Machine Translation System for Spoken Utterances with Limited Resources .............................................................................................. 745

Jason Riesa, Behrang Mohit, Kevin Knight, Daniel Marcu

A Phrase-Level Machine Translation Approach for Disfluency Detection Using Weighted Finite State Transducers............................................................................................... 749

Sameer Maskey, Bowen Zhou, Yuqing Gao

Improving Phrase-Based Korean-English Statistical Machine Translation.............................. 753Jonghoon Lee, Donghyeon Lee, Gary Geunbae Lee

A Hybrid Phrase-Based/Statistical Speech Translation System................................................ 757David Stallard, Fred Choi, Kriste Krstovski, Prem Natarajan, Rohit Prasad, Shirin Saleem

High-Quality Speech Translation in the Flight Domain............................................................... 761Chao Wang, Stephanie Seneff

Optimizing Components for Handheld Two-Way Speech Translation for an English-Iraqi Arabic System .......................................................................................................... 765

Roger Hsiao, Ashish Venugopal, Thilo Kohler, Ying Zhang, Paisarn Charoenpornsawat, Andreas Zollmann, Stephan Vogel, Alan W. Black, Tanja Schultz, Alex Waibel

ACOUSTIC MODELING II – ADAPTION

Distant-Talking Continuous Speech Recognition Based on a Novel Reverberation Model in the Feature Domain ......................................................................................................... 769

Armin Sehr, Marcus Zeller, Walter Kellermann

Robust Feature Space Adaptation for Telephony Speech Recognition ................................... 773Xin Lei, Jon Hamaker, Xiaodong He

A Simulated-Data Adaptation Technique for Robust Speech Recognition .............................. 777Nattanun Thatphithakkul, Boontee Kruatrachue, Chai Wutiwiwatchai, Sanparith Marukatat, Vataya Boonpiam

A New HMM Adaptation Approach for the Case of a Hands-Free Speech Input in Reverberant Rooms ........................................................................................................................ 781

Hans-Gunter Hirsch, Harald Finster

A Vector Space Approach to Environment Modeling for Robust Speech Recognition ..................................................................................................................................... 785

Yu Tsao, Chin-Hui Lee

Subspace Modeling and Selection for Noisy Speech Recognition ........................................... 789Jen-Tzung Chien, Chuan-Wei Ting

EMOTIONAL SPEECH AND SPEAKER STATE

Recognition of Interest in Human Conversational Speech ........................................................ 793Bjorn Schuller, Niels Kohler, Ronald Muller, Gerhard Rigoll

Using System and User Performance Features to Improve Emotion Detection in Spoken Tutoring Dialogs................................................................................................................ 797

Hua Ai, Diane J. Litman, Kate Forbes-Riley, Mihai Rotaru, Joel Tetreault, Amruta Purandare

Real-Life Emotions Detection with Lexical and Paralinguistic Cues on Human-Human Call Center Dialogs ............................................................................................................ 801

Laurence Devillers, Laurence Vidrascu

Real vs. Acted Emotional Speech ................................................................................................. 805Janneke Wilting, Emiel Krahmer, Marc Swerts

Emotion Recognition in Spontaneous Speech Using GMMs ..................................................... 809Daniel Neiberg, Kjell Elenius, Kornel Laskowski

Personality Factors in Human Deception Detection: Comparing Human to Machine Performance..................................................................................................................... 813

Frank Enos, Stefan Benus, Robin L. Cautin, Martin Graciarena, Julia Hirschberg, Elizabeth Shriberg

SPEECH AND LANGUAGE IN EDUCATION

Developing an Automatic Assessment Tool for Children's Oral Reading ................................ 817Leen Cleuren, Jacques Duchateau, Alain Sips, Pol Ghesquiere, Hugo Van Hamme

Prototyping a Call System for Students of Japanese Using Dynamic Diagram Generation and Interactive Hints................................................................................................... 821

Christopher Waple, Yasushi Tsubota, Masatake Dantsuji, Tatsuya Kawahara

A Multilingual Embodied Conversational Agent for Tutoring Speech and Language Learning ......................................................................................................................... 825

Dominic W. Massaro, Ying Liu, Trevor H. Chen, Charles Perfetti

Classroom Success of an Intelligent Tutoring System for Lexical Practice and Reading Comprehension ............................................................................................................... 829

Michael Heilman, Kevyn Collins-Thompson, Jamie Callan, Maxine Eskenazi

Assessing the Reading Level of Web Pages ............................................................................... 833Sarah E. Petersen, Mari Ostendorf

Is ASR Accurate Enough for Automated Reading Tutors, and How Can We Tell? ................. 837Jack Mostow

Development of a Program for Self Assessment of Japanese Pronunciation by English Learners ............................................................................................................................. 841

Chiharu Tsurutani, Yutaka Yamauchi, Nobuaki Minematsu, Dean Luo, Kazutaka Maruyama, Keikichi Hirose

Pronunciation Verification of Children's Speech for Automatic Literacy Assessment ..................................................................................................................................... 845

Joseph Tepperman, Jorge Silva, Abe Kazemzadeh, Hong You, Sungbok Lee, Abeer Alwan, Shrikanth Narayanan

Computer Aided Pronunciation Learning System Using Speech Recognition Techniques ...................................................................................................................................... 849

Sherif Mahdy Abdou, Salah Eldeen Hamid, Mohsen Rashwan, Abdurrahman Samir, Ossama Abdel-Hamid, Mostafa Shahin, Waleed Nazih

SPEECH PERCEPTION I

An Information Theoretic Tool for Investigating Speech Perception ........................................ 853Bryce Lobdell, Jont B. Allen

An Adaptive Sampling Procedure for Speech Perception Experiments................................... 857Geoffrey Stewart Morrison

Disentangling Gestural and Auditory Contrast Accounts of Compensation for Coarticulation .................................................................................................................................. 861

Navin Viswanathan, James S. Magnuson, Carol A. Fowler

The Role of Positional Probability in the Segmentation of Cantonese Speech ....................... 865Michael C. W. Yip

Nasality Perception of Vowels in Different Language Background .......................................... 869Shahina Haque, Tomio Takara

Steady-State Suppression in Reverberation: A Comparison of Native and Nonnative Speech Perception ....................................................................................................... 873

Nao Hodoshima, Dawn Behne, Takayuki Arai

Effect of Dynamic Information of Formants on Discrimination of English Vowels in Consonantal Contexts by Japanese Listeners ........................................................................ 877

Akiyo Joto

Native and Nonnative Audio-Visual Perception of English Fricatives in Quiet and Cafe-Noise Backgrounds ............................................................................................................... 881

Yue Wang, Dawn Behne, Haisheng Jiang, Chad Danyluck

Perceptive and Acoustic Measurement of Average Speaking Pitch of Female and Male Speakers in German Radio News......................................................................................... 885

Sven Grawunder, Ines Bose, Birgit Hertha, Franziska Trauselt, Lutz Christian Anders

Effects of Frequency Shifts on Perceived Naturalness and Gender Information in Speech ............................................................................................................................................. 889

Peter F. Assmann, Sophia Dembling, Terrance M. Nearey

Influence of Pause Length on Listeners' Impressions in Simultaneous Interpretation ................................................................................................................................... 893

Hitomi Tohyama, Shigeki Matsubara

New Measures to Chart Toddlers' Speech Perception and Language Development: A Test of the Lexical Restructuring Hypothesis ................................................. 897

Iris-Corinna Schwarz, Denis Burnham

Perception of Fundamental Frequency in Cochlear Implant Patients....................................... 901Angel De La Torre, Cristina Roldan, Manuel Sainz

SPEAKER CHARACTERIZATION AND RECOGNITION II

Significance of Formants from Difference Spectrum for Speaker Identification ..................... 905Kishore Prahallad, Sudhakar Varanasi, Ranganatham Veluru, Bharat Krishna M., Debashish S. Roy

Using Genetic Algorithms to Weight Acoustic Features for Speaker Recognition ................. 909Maider Zamalloa, German Bordel, Luis Javier Rodriguez, Mikel Penagarikano, Juan Pedro Uribe

Missing Feature Theory with Soft Spectral Subtraction for Speaker Verification ................... 913Michael T. Padilla, Thomas F. Quatieri, Douglas A. Reynolds

Prosodic Features for Speaker Verification ................................................................................. 917Leena Mary, Yegnanarayana B.

Unsupervised Learning of HMM Topology for Text-Dependent Speaker Verification....................................................................................................................................... 921

Ming Liu, Thomas S. Huang

On the Use of Jacobian Adaptation in Real Speaker Verification Applications....................... 925Jan Anguita, Javier Hernando

A Novel Framework of Text-Independent Speaker Verification Based on Utterance Transform and Iterative Cohort Modeling .................................................................................... 929

Ming Liu, Huazhong Ning, Thomas S. Huang, Zhengyou Zhang

A Cohort - UBM Approach to Mitigate Data Sparseness for In-Set/Out-of-Set Speaker Recognition ...................................................................................................................... 933

Vinod Prakash, John H. L. Hansen

Analysis of Lombard Effect Under Different Types and Levels of Noise with Application to In-Set Speaker ID Systems.................................................................................... 937

Vaishnevi S. Varadarajan, John H. L. Hansen

Reducing Speech Coding Distortion for Speaker Identification ................................................ 941Alan McCree

A Text-Prompted Distributed Speaker Verification System Implemented on a Cellular Phone and a Mobile Terminal .......................................................................................... 945

Tsuneo Kato, Hisashi Kawai

Automatic Detection of Irregular Phonation in Continuous Speech ......................................... 949Srikanth Vishnubhotla, Carol Y. Espy-Wilson

SPEECH PRODUCTION, PHYSIOLOGY, AND PATHOLOGY I

Effects of Word Frequency on the Acoustic Durations of Affixes............................................. 953Mark Pluymaekers, Mirjam Ernestus, R. Harald Baayen

A Noninvasive, Low-Cost Device to Study the Velopharyngeal Port During Speech and Some Preliminary Results ........................................................................................ 957

Xiaochuan Niu, Alexander B. Kain, Jan P. H. Van Santen

Characterization of Cued Speech Vowels from the Inner Lip Contour ..................................... 961Noureddine Aboutabit, Denis Beautemps, Laurent Besacier

Modelling Aspiration Noise During Phonation Using the LF Voice Source Model .................. 965Christer Gobl

A Simulation Based Parameter Optimization for a Coarticulation Model ................................. 969Jianguo Wei, Xugang Lu, Jianwu Dang

Multivariate Analysis of Frame-Based Acoustic Cues of Dysperiodicities in Connected Speech.......................................................................................................................... 973

A. Kacha, Francis Grenez, Jean Schoentgen

Effects of Midline Tongue Piercing on Spectral Centroid Frequencies of Sibilants ............... 977Tom Kovacs, Donald S. Finan

Assessment of Articulatory Sub-Systems of Dysarthric Speech Using an Isolated-Style Phoneme Recognition System............................................................................................. 981

P. Vijayalakshmi, M. R. Reddy, Douglas O'Shaughnessy

Respiratory/Laryngeal Interactions During Sustained Vowel Production in Children............................................................................................................................................ 985

Donald S. Finan, Carol A. Boliek

Acoustic Characterization of Children with Speech Delay......................................................... 989H. Timothy Bunnell, James B. Polikoff

Study of Time and Frequency Variability in Pathological Speech and Error Reduction Methods for Automatic Speech Recognition ............................................................ 993

Oscar Saz, Antonio Miguel, Eduardo Lleida, Alfonso Ortega, Luis Buera

FORMANT ESTIMATION

Tracking of Involuntary Formant Frequency Variations and Application to Parkinsonian Speech...................................................................................................................... 997

Laurence Cnockaert, Jean Schoentgen, Pascal Auzou, Canan Ozsancak, Francis Grenez

All-Pole Model Estimation of Vocal Tract on the Frequency Domain ..................................... 1001Luis Weruaga, Amar Al-Khayat

HMM-Based MAP Prediction of Voiced and Unvoiced Formant Frequencies from Noisy MFCC Vectors..................................................................................................................... 1005

Jonathan Darch, Ben Milner

Extracting Formants from Short Segments of Speech Using Group Delay Functions ....................................................................................................................................... 1009

Anand Joseph M., Guruprasad S., Yegnanarayana B.

Tracking of Visible Vocal Tract Resonances (VVTR) Based on Kalman Filtering ................. 1013I Yucel Ozbek, Mubeccel Demirekler

Wavelet Ridge Track Interpretation in Terms of Formants....................................................... 1017Salma Chaari, Kais Ouni, Noureddine Ellouze

LANGUAGE PROCESSING BEYOND AND BELOW THE WORD-LEVEL

Unsupervised Segmentation of Words into Morphemes --- Morpho Challenge 2005 Application to Automatic Speech Recognition................................................................. 1021

Mikko Kurimo, Mathias Creutz, Matti Varjokallio, Ebru Arisoy, Murat Saraclar

Lattice Extension and Rescoring Based Approaches for LVCSR of Turkish......................... 1025Ebru Arisoy, Murat Saraclar

Exploiting Semantic Relations for a Spoken Language Understanding Application ............ 1029Catherine Kobus, Geraldine Damnati, Lionel Delphin-Poulat, Renato De Mori

Sentence Boundary Detection of Spontaneous Japanese Using Statistical Language Model and Support Vector Machines........................................................................ 1033

Yuya Akita, Masahiro Saikou, Hiroaki Nanjo, Tatsuya Kawahara

Compact N-Gram Models by Incremental Growing and Clustering of Histories.................... 1037Sami Virpioja, Mikko Kurimo

Opinion Mining in a Telephone Survey Corpus ......................................................................... 1041Nathalie Camelin, Geraldine Damnati, Frederic Bechet, Renato De Mori

SPOKEN DIALOG SYSTEMS II

A User Simulator Based on VoiceXML for Evaluation of Spoken Dialog Systems................ 1045Akinori Ito, Keisuke Shimada, Motoyuki Suzuki, Shozo Makino

User Expectations and Real Experience on a Multimodal Interactive System....................... 1049Kristiina Jokinen, Topi Hurtig

Detecting Anger in Automated Voice Portal Dialogs ................................................................ 1053F. Burkhardt, J. Ajmera, Roman Englert, J. Stegmann, W. Burleson

VOLUME III

Evaluation of a Spoken Dialogue System with Usability Tests and Long-Term Pilot Studies: Similarities and Differences................................................................................. 1057

Markku Turunen, Jaakko Hakulinen, Anssi Kainulainen

CHAT: A Conversational Helper for Automotive Tasks ............................................................ 1061F. Weng, S. Varges, B. Raghunathan, F. Ratiu, H. Pon-Barry, B. Lathrop, Q. Zhang, H. Bratt, T. Scheideck, K. Xu, M. Purver, R. Mishra, A. Lien, M. Raya, S. Peters, Y. Meng, J. Russell, L. Cavedon, E. Shriberg, H. Schmidt, R. Prieto

User Simulation for Spoken Dialogue Systems: Learning and Evaluation ............................ 1065Kallirroi Georgila, James Henderson, Oliver Lemon

CORPORA, ANNOTATION, AND ASSESSMENT METRICS II

Conversational Quality Estimation Model for Wideband IP-Telephony Services .................. 1069Hitoshi Aoki, Atsuko Kurashima, Akira Takahashi

The Vocal Joystick Data Collection Effort and Vowel Corpus ................................................. 1073Kelley Kilanski, Jonathan Malkin, Xiao Li, Richard Wright, Jeff A. Bilmes

Comparison of the ITU-T P.85 Standard to Other Methods for the Evaluation of Text-to-Speech Systems .............................................................................................................. 1077

Dmitry Sityaev, Katherine Knill, Tina Burrows

An Annotation Scheme for Complex Disfluencies .................................................................... 1081Peter A. Heeman, Andy McMillin, J. Scott Yaruss

Automatic Phonetic Transcription of Large Speech Corpora: A Comparative Study .............................................................................................................................................. 1085

Christophe Van Bael, Lou Boves, Henk Van Den Heuvel, Helmer Strik

Examining Knowledge Sources for Human Error Correction .................................................. 1089Yongmei Shi, Lina Zhou

ROBUSTNESS AND ADAPTATION FOR ASR

An Integrated Solution for Error Concealment in DSR Systems Over Wireless Channels ........................................................................................................................................ 1093

Antonio M. Peinado, Angel M. Gomez, Victoria Sanchez, Jose L. Perez-Cordoba, Antonio J. Rubio

Interleaving and MMSE Estimation with VQ Replicas for Distributed Speech Recognition Over Lossy Packet Networks................................................................................. 1097

Angel M. Gomez, Antonio M. Peinado, Victoria Sanchez, Jose L. Carmona, Antonio J. Rubio

Noise-Robust Speech Recognition of Conversational Telephone Speech ............................ 1101Shaughnessy

Lost Speech Reconstruction Method Using Speech Recognition Based on Missing Feature Theory and HMM-Based Speech Synthesis................................................... 1105

Shingo Kuroiwa, Satoru Tsuge, Fuji Ren

Speaker Adaptation Using Evolutionary-Based Linear Transform ......................................... 1109Sid-Ahmed Selouani, Douglas O'Shaughnessy

A Speaker Adaptation Algorithm Using Principal Curves in Noisy Environments................ 1113Jingying Wang, Zuoying Wang

Limitations of MLLR Adaptation with Spanish-Accented English: An Error Analysis ......................................................................................................................................... 1117

Constance Clarke, Daniel Jurafsky

Issues with Uncertainty Decoding for Noise Robust Speech Recognition ............................ 1121H. Liao, M. J. F. Gales

Vector Taylor Series Based Joint Uncertainty Decoding ......................................................... 1125Haitian Xu, Luca Rigazio, David Kryze

A Maximum Likelihood Training Approach to Irrelevant Variability Compensation Based on Piecewise Linear Transformations ............................................................................ 1129

Qiang Huo, Donglai Zhu

Speaker Clustered Regression-Class Trees for MLLR Adaptation ......................................... 1133Arindam Mandal, Mari Ostendorf, Andreas Stolcke

Robust Speech Recognition Over Mobile Networks Using Combined Weighted Viterbi Decoding and Subvector Based Error Concealment .................................................... 1137

Zheng-Hua Tan, Paul Dalsgaard, Borge Lindberg

Speaker Adaptation of Trajectory HMMs Using Feature-Space MLLR.................................... 1141Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura

Feature and Model Space Speaker Adaptation with Full Covariance Gaussians .................. 1145Daniel Povey, George Saon

MULTIMODAL, TRANSLATION AND INFORMATION RETRIEVAL

Linguistic Tuple Segmentation in Ngram-Based Statistical Machine Translation................. 1149Adria De Gispert, Jose B. Marino

Sentence Boundary Detection Using Sequential Dependency Analysis Combined with CRF-Based Chunking ........................................................................................................... 1153

Takanobu Oba, Takaaki Hori, Atsushi Nakamura

Sequence Classification for Machine Translation..................................................................... 1157Srinivas Bangalore, Patrick Haffner, Stephan Kanthak

Two-Stage Vocabulary-Free Spoken Document Retrieval --- Subword Identification and Re-Recognition of the Identified Sections................................................... 1161

Yoshiaki Itoh, Takayuki Otake, Kohei Iwata, Kazunori Kojima, Masaaki Ishigame, Kazuyo Tanaka, Shi-Wook Lee

Design and Performance Analysis of a Factoid Question Answering System for Spontaneous Speech Transcriptions ......................................................................................... 1165

Mihai Surdeanu, David Dominguez-Sal, Pere R. Comas

Performance Improvement of Dialog Speech Translation by Rejecting Unreliable Utterances...................................................................................................................................... 1169

Toshiyuki Takezawa, Tohru Shimizu

Cross-Lingual Dialog Model for Speech to Speech Translation .............................................. 1173Emil Ettelaie, Panayiotis G. Georgiou, Shrikanth Narayanan

A Robust Fusion Method for Multilingual Spoken Document Retrieval Systems Employing Tiered Resources ...................................................................................................... 1177

Murat Akbacak, John H. L. Hansen

Recent Advances of IBM's Handheld Speech Translation System ......................................... 1181Weizhong Zhu, Bowen Zhou, Charles Prosser, Pavel Krbec, Yuqing Gao

QASR: Question Answering Using Semantic Roles for Speech Interface.............................. 1185Svetlana Stenchikova, Dilek Hakkani-Tur, Gokhan Tur

Towards a Multimodal Topic Tracking System for a Mobile Robot ......................................... 1189Jan F. Maas, Britta Wrede, Gerhard Sagerer

Edge-Splitting in a Cumulative Multimodal System, for a No-Wait Temporal Threshold on Information Fusion, Combined with an Under-Specified Display.................... 1193

Edward C. Kaiser, Paulo Barthelmess

Joint Interpretation of Input Speech and Pen Gestures for Multimodal Human-Computer Interaction.................................................................................................................... 1197

Pui-Yu Hui, Helen M. Meng

ADVANCES IN ACOUSTIC SEGMENTATION

Voice Activity Detector Based on Enhanced Cumulant of LPC Residual and On-Line EM Algorithm ........................................................................................................................ 1201

David Cournapeau, Tatsuya Kawahara, Kenji Mase, Tomoji Toriyama

A Constrained Baum-Welch Algorithm for Improved Phoneme Segmentation and Efficient Training........................................................................................................................... 1205

David Huggins-Daines, Alexander I. Rudnicky

Infinite Models for Speaker Clustering ....................................................................................... 1209Fabio Valente

The Segmentation of Multi-Channel Meeting Recordings for Automatic Speech Recognition ................................................................................................................................... 1213

John Dines, Jithendra Vepa, Thomas Hain

Minimum Boundary Error Training for Automatic Phonetic Segmentation............................ 1217Jen-Wei Kuo, Hsin-Min Wang

Dynamic Evidence Models in a DBN Phone Recognizer .......................................................... 1221William Schuler, Tim Miller, Stephen Wu, Andrew Exley

ACOUSTIC MODELING III – LVCSR

The IBM 2006 Speech Transcription System for European Parliamentary Speeches ....................................................................................................................................... 1225

B. Ramabhadran, Olivier Siohan, L. Mangu, G. Zweig, M. Westphal, H. Schulz, A. Soneiro

Advances in Lecture Recognition: The ISL RT-06S Evaluation System ................................. 1229Christian Fugen, Matthias Wolfel, John W. McDonough, Shajith Ikbal, Florian Kraft, Kornel Laskowski, Mari Ostendorf, Sebastian Stuker, Kenichi Kumatani

Investigation on Mandarin Broadcast News Speech Recognition .......................................... 1233Mei-Yuh Hwang, Xin Lei, Wen Wang, Takahiro Shinozaki

Improved Tone Modeling for Mandarin Broadcast News Speech Recognition...................... 1237Xin Lei, Manhung Siu, Mei-Yuh Hwang, Mari Ostendorf, Tan Lee

Prosodic Modeling in Large Vocabulary Mandarin Speech Recognition ............................... 1241Jui-Ting Huang, Lin-Shan Lee

Experiments on Chinese Speech Recognition with Tonal Models and Pitch Estimation Using the Mandarin Speecon Data .......................................................................... 1245

Ying Sun, Daniel Willett, Raymond Brueckner, Rainer Gruhn, Dirk Buhler

LINGUISTICS, PHONOLOGY, AND PHONETICS II

A Model of the Regularities Underlying Speaker Variation: Evidence from Hybrid Synthesis ....................................................................................................................................... 1249

Susan R. Hertz

Pauses as a Tool to Ensure Rhythmic Wellformedness........................................................... 1253Augustin Speyer

Factors Affecting Speakers' Choice of Fillers in Japanese Presentations............................. 1256Michiko Watanabe, Yasuharu Den, Keikichi Hirose, Shusaku Miwa, Nobuaki Minematsu

Developing Consistent Pronunciation Models for Phonemic Variants................................... 1260Marelie Davel, Etienne Barnard

Grapheme-to-Phoneme Conversion Using Automatically Extracted Associative Rules for Korean TTS System ..................................................................................................... 1264

Jinsik Lee, Seungwon Kim, Gary Geunbae Lee

Example-Based Grapheme-to-Phoneme Conversion for Thai ................................................. 1268Paisarn Charoenpornsawat, Tanja Schultz

SPEECH AN DVISUAL PROCESSING

Visual Correlates to Prominence in Several Expressive Modes .............................................. 1272Jonas Beskow, Bjorn Granstrom, David House

How Auditory and Visual Prosody is Used in End-of-Utterance Detection ............................ 1276Pashiera Barkhuysen, Emiel Krahmer, Marc Swerts

The Importance of Different Facial Areas for Signalling Visual Prominence ......................... 1280Marc Swerts, Emiel Krahmer

Visual Speech Segmentation and Speaker Recognition for Transcription of TV News ............................................................................................................................................... 1284

Josef Chaloupka

HMM-Based Continuous Sign Language Recognition Using a Fast Optical Flow Parameterization of Visual Information ...................................................................................... 1288

G. Cortes, L. Garcia, Carmen Benitez, Jose C. Segura

Audio-Visual Speech Recognition in the Presence of a Competing Speaker ........................ 1292Xu Shao, Jon Barker

TTS I

Expressive Prosody for Unit-Selection Speech Synthesis....................................................... 1296Volker Strom, Robert A. J. Clark, Simon King

Cues for Hesitation in Speech Synthesis ................................................................................... 1300Rolf Carlson, Kjell Gustafson, Eva Strangert

Multi-Domain Text-to-Speech Synthesis by Automatic Text Classification ........................... 1304Francesc Alias, Joan Claudi Socoro, Xavier Sevillano, Ignasi Iriondo, Xavier Gonzalvo

Phrase Break Prediction Using Logistic Generalized Linear Model........................................ 1308Lifu Yi, Jian Li, Xiaoyan Lou, Jie Hao

Joint Prosodic and Segmental Unit Selection Speech Synthesis ........................................... 1312Robert A. J. Clark, Simon King

Phonetically Enriched Labeling in Unit Selection TTS Synthesis ........................................... 1316Yeon-Jun Kim, Ann K. Syrdal, Alistair Conkie, Mark C. Beutnagel

Further Developments in LSM-Based Boundary Training for Unit Selection TTS ................. 1320Jerome R. Bellegarda

A Style Control Technique for Speech Synthesis Using Multiple Regression HSMM ............................................................................................................................................. 1324

Takashi Nose, Junichi Yamagishi, Takao Kobayashi

Acoustic Model Training Based on Linear Transformation and MAP Modification for HSMM-Based Speech Synthesis ........................................................................................... 1328

Katsumi Ogata, Makoto Tachibana, Junichi Yamagishi, Takao Kobayashi

Improving Arabic HMM Based Speech Synthesis Quality........................................................ 1332Ossama Abdel-Hamid, Sherif Mahdy Abdou, Mohsen Rashwan

FarsBayan: A Unit Selection Based Farsi Speech Synthesizer ............................................... 1336M. Mehdi Homayounpour, Majid Namnabat

Amharic Speech Synthesis Using Cepstral Method with Stress Generation Rule ................ 1340Tadesse Anberbir, Tomio Takara

Automatic Syllable-Pattern Induction in Statistical Thai Text-to-Phone Transcription ................................................................................................................................. 1344

Ausdang Thangthai, Chatchawarn Hansakunbuntheung, Rungkarn Siricharoenchai, Chai Wutiwiwatchai

Development of Prototype Text-to-Speech Systems for Northern Sotho............................... 1348H. J. Oosthuizen, S. T. Phihlela, M. J. D. Manamela

Identify Language Origin of Personal Names with Normalized Appearance Number of Web Pages .................................................................................................................. 1352

Jiali You, Yining Chen, Min Chu, Yong Zhao, Jinlin Wang

SPECIAL POPULATIONS – LEARNERS, AGED, CHALLENGED

Observations of the Spoken Language Acquisition Process Based on a Multimodal Infant Behavior Corpus ............................................................................................ 1356

Ryo Tsuji, Tomohiko Kasami, Shogo Ishikawa, Shinya Kiriyama, Yoichi Takebayashi, Shigeyoshi Kitazawa

Infants' Ability to Extract Verbs from Continuous Speech....................................................... 1360Ellen Marklund, Francisco Lacerda

Category Formation and the Role of Spectral Quality in the Perception and Production of English Front Vowels ........................................................................................... 1363

Ricardo A. H. Bion, Paola Escudero, Andreia S. Rauber, Barbara O. Baptista

Productions in Bilinguism, Early Foreign Language Learning and Monolinguism: A Prosodic Comparison ............................................................................................................... 1367

Ranka Bijeljac-Babic, Christelle Dodane, Sabine Metta, Claire Gerard

Training Native English Speakers to Identify Japanese Vowel Length with Fast Rate Sentences ............................................................................................................................. 1371

Yukari Hirata, Elizabeth Whitehurst, Emily Cullings, Jacob Whiton, Carol Glenn

Formant-Based English Vowel Assessment for Chinese in Taiwan ....................................... 1375Jiang-Chun Chen, Wei-Tang Hsu, J.-S. Roger Jang, Ren-Yuan Lyu, Yuang-Chin Chiang

Substitute Sounds for Ventriloquism and Speech Disorders .................................................. 1379Jorg Metzner, Marcel Schmittfull, Karl Schnell

Automatic Mandarin Pronunciation Scoring for Native Learners with Dialect Accent ............................................................................................................................................ 1383

Si Wei, Qing-Sheng Liu, Yu Hu, Ren-Hua Wang

Quick Individual Fitting Methods of Simplified Hearing Compensation for Elderly People............................................................................................................................................. 1387

Kengo Fujita, Tsuneo Kato, Hisashi Kawai

An Online Adaptive Filtering Algorithm for the Vocal Joystick ............................................... 1391Xiao Li, Jonathan Malkin, Susumu Harada, Jeff A. Bilmes, Richard Wright, James Landay

Speaking Aid System for Total Laryngectomees Using Voice Conversion of Body Transmitted Artificial Speech ...................................................................................................... 1395

Keigo Nakamura, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano

A Spanish Speech to Sign Language Translation System for Assisting Deaf-Mute People............................................................................................................................................. 1399

R. San-Segundo, R. Barra, L. F. D'Haro, J. M. Montero, R. Cordoba, J. Ferreiros

Potential Relevance of Audio-Visual Integration in Mammals for Computational Modeling ........................................................................................................................................ 1403

Eeva Klintfors, Francisco Lacerda

Finding the Gaps: Applying a Connectionist Model of Word Segmentation to Noisy Phone-Recognized Speech Data ...................................................................................... 1407

C. Anton Rytting

SPEECH ENHANCEMENT II

Single Channel Speech Enhancement by Frequency Domain Constrained Optimization and Temporal Masking .......................................................................................... 1411

Wen Jin, Michael Scordilis

Speech Enhancement Based on Residual Noise Shaping ....................................................... 1415Jong Won Shin, Seung Yeol Lee, Hwan Sik Yun, Nam Soo Kim

Quality Improvement of Telephone Speech by Artificial Bandwidth Expansion --- Listening Tests in Three Languages........................................................................................... 1419

Hannu Pulakka, Laura Laaksonen, Paavo Alku

Role of Phase Estimation in Speech Enhancement .................................................................. 1423Benjamin J. Shannon, Kuldip K. Paliwal

Speech Enhancement Based on Spectral Estimation from Higher-Lag Autocorrelation ............................................................................................................................. 1427

Benjamin J. Shannon, Kuldip K. Paliwal, Climent Nadeu

Noise Update Modeling for Speech Enhancement: When Do We Do Enough? ..................... 1431Nitish Krishnamurthy, John H. L. Hansen

Mapping Neural Networks for Bandwidth Extension of Narrowband Speech........................ 1435A. Shahina, Yegnanarayana B.

Decision Directed Constrained Iterative Speech Enhancement .............................................. 1439Amit Das, John H. L. Hansen

Adaptive Filtering for Attenuating Musical Noise Caused by Spectral Subtraction .............. 1443Takahiro Murakami, Yoshihisa Ishida

Evaluation of Objective Measures for Speech Enhancement .................................................. 1447Yi Hu, Philipos C. Loizou

Performance Analysis of Various Single Channel Speech Enhancement Algorithms for Automatic Speech Recognition ......................................................................... 1451

Myung-Suk Song, Chang-Heon Lee, Hong-Goo Kang

SPEAKER CHARACTERIZATION AND RECOGNITION III

Highly Noise Robust Text-Dependent Speaker Recognition Based on Hypothesized Wiener Filtering .................................................................................................... 1455

Ramasubramanian V., Deepak Vijaywargiay, Praveen Kumar V.

Speaker Identification Under Noisy Environments by Using Harmonic Structure Extraction and Reliable Frame Weighting .................................................................................. 1459

Hiromasa Fujihara, Tetsuro Kitahara, Masataka Goto, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

Enhancing the Performance of a GMM-Based Speaker Identification System in a Multi-Microphone Setup ............................................................................................................... 1463

Andreas Stergiou, Aristodemos Pnevmatikakis, Lazaros C. Polymenakos

Discriminative Adaptation for Speaker Verification .................................................................. 1467C. Longworth, M. J. F. Gales

Within-Class Covariance Normalization for SVM-Based Speaker Recognition ..................... 1471Andrew O. Hatch, Sachin Kajarekar, Andreas Stolcke

A New Set of Features for Text-Independent Speaker Identification ...................................... 1475Carol Y. Espy-Wilson, Sandeep Manocha, Srikanth Vishnubhotla

ROBUST ASR

Rapid Speaker Adaptation Using Regression-Tree Based Spectral Peak Alignment....................................................................................................................................... 1479

Shizhen Wang, Xiaodong Cui, Abeer Alwan

Physiologically-Motivated Synchrony-Based Processing for Robust Automatic Speech Recognition...................................................................................................................... 1483

Chanwoo Kim, Yu-Hsiang Chiu, Richard M. Stern

Sub-Word Unit Based Non-Audible Speech Recognition Using Surface Electromyography......................................................................................................................... 1487

Matthias Walliczek, Florian Kraft, Szu-Chen Jou, Tanja Schultz, Alex Waibel

Individual On-Line Variance Adaptation of Frequency Filtered Parameters for Robust ASR ................................................................................................................................... 1491

Jesus Vicente-Pena, Fernando Diaz-De-Maria, Bastiaan Kleijn

Recent Progress on the Discriminative Region-Dependent Transform for Speech Feature Extraction......................................................................................................................... 1495

Bing Zhang, Spyros Matsoukas, Richard Schwartz

Improved Warping-Invariant Features for Automatic Speech Recognition............................ 1499Jan Rademacher, Matthias Wachter, Alfred Mertins

SPEECH PERCEPTION II

Effects of Featural Similarity and Overlap Position on Lexical Confusions and Overt Similarity Judgments ......................................................................................................... 1503

Sarah C. Creel, Delphine Dahan, Daniel Swingley

Word Structure and Tone Perception in Mandarin .................................................................... 1507Hansjorg Mixdorff, Yu Hu

Identification of Regional Accents in French: Perception and Categorization ...................... 1511Cecile Woehrling, Philippe Boula De Mareuil

Consonant and Vowel Confusions in Speech-Weighted Noise ............................................... 1515Sandeep Phatak, Jont B. Allen

Accident -- Execute: Increased Activation in Nonnative Listening ......................................... 1519Mirjam Broersma

Estimation of the Quality Dimension ``Directness/Frequency Content'' for the Instrumental Assessment of Speech Quality............................................................................. 1523

Kirstin Scholz, Marcel Waltermann, Lu Huo, Alexander Raake, Sebastian Moller, Ulrich Heute

SPEECH SUMMARIZATION

Summarization Evaluation for Text and Speech: Issues and Approaches............................. 1527Ani Nenkova

Summarization of Spontaneous Conversations ........................................................................ 1531Xiaodan Zhu, Gerald Penn

Perplexity Based Linguistic Model Adaptation for Speech Summarisation........................... 1535Pierre Chatain, Edward Whittaker, Joanna Mrozinski, Sadaoki Furui

Multi-Layered Summarization of Spoken Document Archives by Information Extraction and Semantic Structuring.......................................................................................... 1539

Lin-Shan Lee, Sheng-Yi Kong, Yi-Cheng Pan, Yi-Sheng Fu, Yu-Tsun Huang

Soundbite Detection in Broadcast News Domain ..................................................................... 1543Sameer Maskey, Julia Hirschberg

Dialogue Act Compression via Pitch Contour Preservation .................................................... 1547Gabriel Murray, Steve Renals

ACOUSTIC MODELING IV

Manifold HLDA and Its Application to Robust Speech Recognition ....................................... 1551Toshiaki Kubo, Tetsuji Ogawa, Tetsunori Kobayashi

Time-Dependent Cross-Probability Model for Multi-Environment Model Based LInear Normalization..................................................................................................................... 1555

Luis Buera, Eduardo Lleida, Juan A. Nolazco-Flores, Antonio Miguel, Alfonso Ortega

SPAM and Full Covariance for Speech Recognition ................................................................. 1559Daniel Povey

The Use of Bayesian Network for Incorporating Accent, Gender and Wide-Context Dependency Information .............................................................................................................. 1563

Sakriani Sakti, Konstantin Markov, Satoshi Nakamura

Integrating Phonetic Boundary Discrimination Explicitly into HMM Systems ....................... 1567Yu Wang, Eric Fosler-Lussier

Robust Acoustic-Based Syllable Detection ............................................................................... 1571Zhimin Xie, Partha Niyogi

A Tone Recognition Framework for Continuous Mandarin Speech ........................................ 1575Lei He, Jie Hao

Pronunciation Variant-Based Multi-Path HMMs for Syllables .................................................. 1579Annika Hamalainen, Louis Ten Bosch, Lou Boves

VOLUME IV

A New State-Dependent Phonetic Tied-Mixture Model with Head-Body-Tail Structured HMM for Real-Time Continuous Phoneme Recognition System .......................... 1583

Junho Park, Hanseok Ko

Conversion from Phoneme Based to Grapheme Based Acoustic Models for Speech Recognition...................................................................................................................... 1587

Andrej Zgank, Zdravko Kacic

Phone Vector DHMM to Decode a Phone Recognizer's Output ............................................... 1591Bong-Wan Kim, Dae-Lim Choi, Yongnam Um, Yong-Ju Lee

Combining Multiple-Sized Sub-Word Units in a Speech Recognition System Using Baseform Selection ........................................................................................................... 1595

T. Nagarajan, P. Vijayalakshmi, Douglas O'Shaughnessy

Local Transformation Models for Speech Recognition ............................................................ 1598Antonio Miguel, Eduardo Lleida, Alfons Juan, Luis Buera, Alfonso Ortega, Oscar Saz

LARGE VOCABULARY SPEECH RECOGNITION

Online Speech Detection and Dual-Gender Speech Recognition for Captioning Broadcast News ............................................................................................................................ 1602

Toru Imai, Shoei Sato, Akio Kobayashi, Kazuo Onoe, Shinichi Homma

Automatic Alignment and Error Correction of Human Generated Transcripts for Long Speech Recordings............................................................................................................. 1606

Timothy J. Hazen

Improving Speech Recognition Accuracy with Multi-Confidence Thresholding ................... 1610Shuangyu Chang

Conceptual Decoding from Word Lattices: Application to the Spoken Dialogue Corpus MEDIA ............................................................................................................................... 1614

Christophe Servan, Christian Raymond, Frederic Bechet, Pascal Nocera

Improving the Performance of Out-of-Vocabulary Word Rejection by Using Support Vector Machines............................................................................................................. 1618

Shilei Huang, Xiang Xie, Jingming Kuang

Robust Phone Lattice Decoding.................................................................................................. 1622Kris Demuynck, Dirk Van Compernolle, Hugo Van Hamme

Imperfect Transcript Driven Speech Recognition ..................................................................... 1626Benjamin Lecouteux, Georges Linares, Pascal Nocera, Jean-Francois Bonastre

New Improvements in Decoding Speed and Latency for Automatic Captioning ................... 1630Jian Xue, Rusheng Hu, Yunxin Zhao

Colloquial Iraqi ASR for Speech Translation ............................................................................. 1634Shirin Saleem, Rohit Prasad, Prem Natarajan

Reducing Computation on Parallel Decoding Using Frame-Wise Confidence Scores ............................................................................................................................................ 1638

Tomohiro Hakamata, Akinobu Lee, Yoshihiko Nankaku, Keiichi Tokuda

Posterior Based Keyword Spotting with a priori Thresholds................................................... 1642Hamed Ketabdar, Jithendra Vepa, Samy Bengio, Herve Bourlard

A Multi-Pass Error Detection and Correction Framework for Mandarin LVCSR .................... 1646Zhengyu Zhou, Helen M. Meng, Wai Kit Lo

Continual On-Line Monitoring of Czech Spoken Broadcast Programs .................................. 1650Jan Nouza, Jindrich Zdansky, Petr Cerva, Jan Kolorenc

SPEECH/NOISE/MUSIC SEGMENTATION

Fast SVM Training Based on the Choice of Effective Samples for Audio Classification ................................................................................................................................. 1654

Shilei Zhang, Hongchen Jiang, Shuwu Zhang, Bo Xu

Online Speaker Change Detection by Combining BIC with Microphone Array Beamforming ................................................................................................................................. 1658

Joerg Schmalenstroeer, Reinhold Haeb-Umbach

Speech/Non-Speech Discrimination Combining Advanced Feature Extraction and SVM Learning ................................................................................................................................ 1662

Javier Ramirez, Pablo Yelamos, J. M. Gorriz, Jose C. Segura, L. Garcia

Cooperation Between Global and Local Methods for the Automatic Segmentation of Speech Synthesis Corpora ...................................................................................................... 1666

Safaa Jarifi, Dominique Pastor, Olivier Rosec

Speaker Independent Voiced-Unvoiced Detection Evaluated in Different Speaking Styles.............................................................................................................................................. 1670

Martin Heckmann, Marco Moebus, Frank Joublin, Christian Goerick

Robust Speaker Diarization for Meetings: ICSI RT06s Evaluation System ............................ 1674Xavier Anguera, Chuck Wooters, Jose M. Pardo

A Multipitch Tracker for Monaural Speech Segmentation........................................................ 1678Andre Coy, Jon Barker

Novel Entropy Based Moving Average Refiners for HMM Landmarks.................................... 1682Rahul Chitturi, Mark Hasegawa Johnson

Two-Microphone Voice Activity Detection in the Presence of Coherent Interference.................................................................................................................................... 1686

Gibak Kim, Nam Ik Cho

On a Greedy Learning Algorithm for dPLRM with Applications to Phonetic Feature Detection.......................................................................................................................... 1690

Tor Andre Myrvoll, Tomoko Matsui

PITCH ESTIMATION

Improving Glottal Waveform Estimation Through Rank-Based Glottal Quality Assessment ................................................................................................................................... 1694

Elliot Moore II, Juan Torres

A Pitch Marks Filtering Algorithm Based on Restricted Dynamic Programming .................. 1698Francesc Alias, Carlos Monzo, Joan Claudi Socoro

Analysis of Nonmodal Phonation Using Minimum Entropy Deconvolution ........................... 1702Nicolas Malyska, Thomas F. Quatieri

An Automatic Singing Skill Evaluation Method for Unknown Melodies Using Pitch Interval Accuracy and Vibrato Features ..................................................................................... 1706

Tomoyasu Nakano, Masataka Goto, Yuzuru Hiraga

A Spectral-Temporal Method for Pitch Tracking ....................................................................... 1710Stephen A. Zahorian, Princy Dikshit, Hongbing Hu

Pitch Determination Using Aligned AMDF ................................................................................. 1714M. Shahidur Rahman, Hirobumi Tanaka, Tetsuya Shimamura

ACOUSTIC MODELING V – NOVEL APPROACHES

Syllable-Length Path Mixture Hidden Markov Models with Trajectory Clustering for Continuous Speech Recognition........................................................................................... 1718

Yan Han, Lou Boves

Acoustic Modeling for Spoken Dialogue Systems Based on Unsupervised Utterance-Based Selective Training............................................................................................ 1722

Tobias Cincarek, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano

GMM-Based Acoustic Modeling for Embedded Speech Recognition ..................................... 1726Christophe Levy, Georges Linares, Jean-Francois Bonastre

Boosting HMM Performance with a Memory Upgrade .............................................................. 1730Mathias De Wachter, Kris Demuynck, Dirk Van Compernolle

An Integrated Approach to Improve Speech Recognition Rate for Non-Native Speakers ........................................................................................................................................ 1734

Y. Deng, X. Li, C. Kwan, R. Xu, B. Raj, Richard M. Stern, D. Williamson

Bayesian Decision Tree State Tying for Conversational Speech Recognition ...................... 1738Rusheng Hu, Yunxin Zhao

CORPUS-BASED SYNTHESIS

Feature Extraction for Spectral Continuity Measures in Concatenative Speech Synthesis ....................................................................................................................................... 1742

Barry Kirkpatrick, Darragh O'Brien, Ronan Scaife

Decision Tree-Based Training of Probabilistic Concatenation Models for Corpus-Based Speech Synthesis ............................................................................................................. 1746

Shinsuke Sakai, Tatsuya Kawahara

Constructing Stylistic Synthesis Databases from Audio Books ............................................. 1750Yong Zhao, Di Peng, Lijuan Wang, Min Chu, Yining Chen, Peng Yu, Jun Guo

Expanding Phonetic Coverage in Unit Selection Synthesis Through Unit Substitution from a Donor Voice ................................................................................................. 1754

Alistair Conkie, Ann K. Syrdal

Unifying Unit Selection and Hidden Markov Model Speech Synthesis ................................... 1758Paul Taylor

CLUSTERGEN: A Statistical Parametric Synthesizer Using Trajectory Modeling ................. 1762Alan W. Black

SPOKEN DIALOG TECHNOLOGY R&D

Cluster-Based User Simulations for Learning Dialogue Strategies ........................................ 1766Verena Rieser, Oliver Lemon

Prompt Selection with Reinforcement Learning in an AT&T Call Routing Application..................................................................................................................................... 1770

Charles Lewis, Giuseppe Di Fabbrizio

Developing Speech Dialogs for Multimodal HMIs Using Finite State Machines .................... 1774Silke Goronzy, Raquel Mochales, Nicole Beringer

Development of Advanced Dialog Systems with PATE ............................................................ 1778Norbert Pfleger, Jan Schehl

A Joint Intention-Based Dialogue Engine .................................................................................. 1782Rajah Annamalai Subramanian, Philip Cohen

MeMo: Towards Automatic Usability Evaluation of Spoken Dialogue Services by User Error Simulations ................................................................................................................. 1786

Sebastian Moller, Roman Englert, Klaus Engelbrecht, Verena Hafner, Anthony Jameson, Antti Oulasvirta, Alexander Raake, Norbert Reithinger

MODELING SPEAKER EMOTIONAL STATE

Synthesizing Breathiness in Natural Speech with Sinusoidal Modelling ............................... 1790Brett Matthews, Raimo Bakis, Ellen Eide

Voice GMM Modelling for FESTIVAL/MBROLA Emotive TTS Synthesis................................. 1794Mauro Nicolao, Carlo Drioli, Piero Cosi

EmoVoice: A System to Generate Emotions in Speech ........................................................... 1798Joao P. Cabral, Luis C. Oliveira

Real-Time Synthesis of Chinese Visual Speech and Facial Expressions Using MPEG-4 FAP Features in a Three-Dimensional Avatar ............................................................. 1802

Zhiyong Wu, Shen Zhang, Lianhong Cai, Helen M. Meng

Modeling the Acoustic Correlates of Expressive Elements in Text Genres for Expressive Text-to-Speech Synthesis ........................................................................................ 1806

Hongwu Yang, Helen M. Meng, Lianhong Cai

Automatic Emotion Recognition of Speech Signal in Mandarin.............................................. 1810Sheng Zhang, P. C. Ching, Fanrang Kong

Feature Analysis for Emotion Recognition from Mandarin Speech Considering the Special Characteristics of Chinese Language .................................................................... 1814

Yi-Hao Kao, Lin-Shan Lee

Timing Levels in Segment-Based Speech Emotion Recognition ............................................ 1818Bjorn Schuller, Gerhard Rigoll

Analyzing Dialogue Data for Real-World Emotional Speech Classification ........................... 1822Ryuichi Nisimura, Souji Omae, Hideki Kawahara, Toshio Irino

Evolving Emotional Prosody ....................................................................................................... 1826Cecilia Ovesdotter Alm, Xavier Llora

Vocal Emotion Recognition with Cochlear Implants................................................................. 1830Xin Luo, Qian-Jie Fu, John J. Galvin III

Emotion Detection in Infants' Cries Based on a Maximum Likelihood Approach ................. 1834S. Matsunaga, S. Sakaguchi, M. Yamashita, S. Miyahara, S. Nishitani, K. Shinohara

"Yeah Right'': Sarcasm Recognition for Spoken Dialogue Systems....................................... 1838 Joseph Tepperman, David Traum, Shrikanth Narayanan

Identification of Confusion and Surprise in Spoken Dialog Using Prosodic Features ......................................................................................................................................... 1842

Rohit Kumar, Carolyn P. Rose, Diane J. Litman

Analysis and Detection of Speech Under Sleep Deprivation ................................................... 1846Tin Lay Nwe, Haizhou Li, Minghui Dong

Language, Gender, Speaking Style and Language Proficiency as Factors Influencing the Autonomous Vocalic Filler Production in Spontaneous Speech.................. 1850

Ioana Vasilescu, Martine Adda-Decker

LANGUAGE MODELING AND ASR APPLICATIONS

How to Handle Gender and Number Agreement in Statistical Language Models? ............... 1854Caroline Lavecchia, Kamel Smaili, Jean-Paul Haton

Prosodic Features for a Maximum Entropy Language Model .................................................. 1858Oscar Chan, Roberto Togneri

Language Model Adaptation with a Word List and a Raw Corpus .......................................... 1862Shinsuke Mori

Topic-Based Language Modeling with Dynamic Bayesian Networks ..................................... 1866Pascal Wiggers, Leon J. M. Rothkrantz

Speech Recognition of Foreign Out-of-Vocabulary Words Using a Hierarchical Language Model............................................................................................................................ 1870

Hirofumi Yamamoto, Genichiro Kikui, Satoshi Nakamura, Yoshinori Sagisaka

Language Modeling of Chinese Personal Names Based on Character Units for Continuous Chinese Speech Recognition ................................................................................. 1874

Xinhui Hu, Hirofumi Yamamoto, Genichiro Kikui, Yoshinori Sagisaka

A Syllable Based Continuous Speech Recognizer for Tamil ................................................... 1878Lakshmi A., Hema A. Murthy

Spontaneous Thai Speech Recognition ..................................................................................... 1882Monika Woszczyna, Paisarn Charoenpornsawat, Tanja Schultz

Acoustic Analysis and Automatic Recognition of Spontaneous Children's Speech ............ 1886M. Gerosa, D. Giuliani, Shrikanth Narayanan

Speech and Speech Recognition During Dictation Corrections.............................................. 1890Keith Vertanen

Comparison of Keyword Spotting Methods for Searching in Speech .................................... 1894Lubos Smidl, Josef V. Psutka

Automatic Generation of Statistical Language Models for Interactive Voice Response Applications ................................................................................................................ 1898

Mithun Balakrishna, Cyril Cerovic, Dan Moldovan, Ellis Cave

Call Analysis with Classification Using Speech and Non-Speech Features .......................... 1902Yun-Cheng Ju, Ye-Yi Wang, Alex Acero

SPOKEN LANGUAGE UNDERSTANDING

A Spoken Language Understanding Approach Using Successive Learners ......................... 1906Wei-Lin Wu, Ru-Zhan Lu, Hui Liu, Feng Gao

Conversational Help Desk: Vague Callers and Context Switch ............................................... 1910Osamuyimen Stewart, Juan Huerta, Ea-Ee Jan, Cheng Wu, Xiang Li, David Lubensky

Integrating Spoken Dialog and Question Answering: The Ritel Project ................................. 1914Sophie Rosset, Olivier Galibert, Gabriel Illouz, Aurelien Max

Rapid Simulation-Driven Reinforcement Learning of Multimodal Dialog Strategies in Human-Robot Interaction......................................................................................................... 1918

Thomas Prommer, Hartwig Holzapfel, Alex Waibel

Software Architectures for Incremental Understanding of Human Speech ........................... 1922Gregory Aist, James Allen, Ellen Campana, Lucian Galescu, Carlos A. Gomez Gallo, Scott C. Stoness, Mary Swift, Michael Tanenhaus

Lingua Machinae --- An Unorthodox Proposal .......................................................................... 1926Florian Schiel, Christoph Draxler, Marion Libossek

Evaluation of Content Presentation Strategies for an In-car Spoken Dialogue System ........................................................................................................................................... 1930

Heather Pon-Barry, Fuliang Weng, Sebastian Varges

On Designing Context Sensitive Language Models for Spoken Dialog Systems .................. 1934Vaibhava Goel, Ramesh Gopinath

Using SVM and Error-Correcting Codes for Multiclass Dialog Act Classification in Meeting Corpus ............................................................................................................................. 1938

Yang Liu

A Multilingual Expectations Model for Contextual Utterances in Mixed-Initiative Spoken Dialogue ........................................................................................................................... 1942

Hartwig Holzapfel, Alex Waibel

Dynamic Help Generation by Estimating User's Mental Model in Spoken Dialogue Systems ......................................................................................................................................... 1946

Yuichiro Fukubayashi, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

Dialog Act Tagging with Support Vector Machines and Hidden Markov Models................... 1950Dinoj Surendran, Gina-Anne Levow

SEGMENTATION AND VAD

Noise Robust Model-Based Voice Activity Detection ............................................................... 1954Angel De La Torre, Javier Ramirez, Carmen Benitez, Jose C. Segura, L. Garcia, Antonio J. Rubio

Auto-Segmentation Based VAD for Robust ASR ...................................................................... 1958Yu Shi, Frank K. Soong, Jian-Lai Zhou

Improved Speech Activity Detection Using Cross-Channel Features for Recognition of Multiparty Meetings ............................................................................................ 1962

Kofi Boakye, Andreas Stolcke

Evaluation of Voice Activity Detection by Combining Multiple Features with Weight Adaptation ........................................................................................................................ 1966

Yusuke Kida, Tatsuya Kawahara

Voice Activity Detection in Personal Audio Recordings Using Autocorrelogram Compensation ............................................................................................................................... 1970

Keansub Lee, Daniel P. W. Ellis

Discriminating Speech and Non-Speech with Regularized Least Squares ............................ 1974Ryan Rifkin, Nima Mesgarani

TECHNOLOGIES FOR SPECIFIC POPULATIONS: LEARNERS AND CHALLENGED

Automatic Grammar Correction for Second-Language Learners............................................ 1978John Lee, Stephanie Seneff

ASR-Based Corrective Feedback on Pronunciation: Does It Really Work? ........................... 1982Ambra Neri, Catia Cucchiarini, Helmer Strik

Evaluating Prosody of Mandarin Speech for Language Learning ........................................... 1986Minghui Dong, Haizhou Li, Tin Lay Nwe

Spoken Language Technologies Applied to Digital Talking Books ........................................ 1990Isabel Trancoso, Carlos Duarte, Antonio Serralheiro, Diamantino Caseiro, Luis Carrico, Ceu Viana

Building an English Speech Synthesis System from a Japanese ALS Patient's Voice............................................................................................................................................... 1994

Akemi IIda, Jun Ito, Shimpei Kajima, Tsutomu Sugawara

Multi-Modal System ICANDO: Intellectual Computer AssistaNt for Disabled Operators ....................................................................................................................................... 1998

Alexey Karpov, Andrey Ronzhin, Alexandre Cadiou

THE PROSODY OF TURN-TAKING AND DIALOG ACTS

User Responses to Prosodic Variation in Fragmentary Grounding Utterances in Dialog ............................................................................................................................................. 2002

Gabriel Skantze, David House, Jens Edlund

Analysis of Prosodic and Linguistic Cues of Phrase Finals for Turn-Taking and Dialog Acts .................................................................................................................................... 2006

Carlos Toshinori Ishi, Hiroshi Ishiguro, Norihiro Hagita

VOLUME V

From Reaction to Prediction: Experiments with Computational Models of Turn-Taking............................................................................................................................................. 2010

David Schlangen

On Speaker-Specific Prosodic Models for Automatic Dialog Act Segmentation of Multi-Party Meetings ..................................................................................................................... 2014

Jachym Kolar, Elizabeth Shriberg, Yang Liu

A Case Study in the Identification of Prosodic Cues to Turn-Taking: Back-Channeling in Arabic .................................................................................................................... 2018

Nigel G. Ward, Yaffa Al Bayyari

family /nailon/ --- Software for Online Analysis of Prosody ..................................................... 2022Jens Edlund, Mattias Heldner

TTS II

Conditional Random Fields for Hierarchical Segment Selection in Text-to-Speech Synthesis ....................................................................................................................................... 2026

Christian Weiss, Wolfgang Hess

Corpus Design Based on the Kullback-Leibler Divergence for Text-to-Speech Synthesis Application................................................................................................................... 2030

Aleksandra Krul, Geraldine Damnati, Francois Yvon, Thierry Moudenc

HMM-Based Unit Selection Using Frame Sized Speech Segments ......................................... 2034Zhen-Hua Ling, Ren-Hua Wang

The Target Cost Formulation in Unit Selection Speech Synthesis ......................................... 2038Paul Taylor

Unit Selection and Its Relation to Symbolic Prosody: A New Approach ................................ 2042Daniel Tihelka, Jindrich Matousek

Minimum Generation Error Criterion for Tree-Based Clustering of Context Dependent HMMs .......................................................................................................................... 2046

Yi-Jian Wu, Wu Guo, Ren-Hua Wang

Selective-LPC Based Representation of STRAIGHT Spectrum and Its Applications in Spectral Smoothing .................................................................................................................. 2050

Heng Kang, Wenju Liu

Towards a Comprehensive Investigation of Factors Relevant to Peak Alignment Using a Unit Selection Corpus .................................................................................................... 2054

Matthias Jilka, Bernd Mobius

Six Approaches to Limited Domain Concatenative Speech Synthesis................................... 2058Robert J. Utama, Ann K. Syrdal, Alistair Conkie

From Pre-Recorded Prompts to Corporate Voices: On the Migration of Interactive Voice Response Applications...................................................................................................... 2062

V. Fischer, S. Kunzmann

Automatic Speech Segmentation with Multiple Statistical Models ......................................... 2066Seung Seop Park, Jong Won Shin, Nam Soo Kim

Evaluation of Perceptual Quality of Control Point Reduction in Rule-Based Synthesis ....................................................................................................................................... 2070

Kimmo Parssinen, Marko Moberg

Segment Connection Networks for Corpus-Based Speech Synthesis ................................... 2074Geert Coorman

SPEAKER CHARACTERIZATION AND RECOGNITION IV

Detection of a Third Speaker in Telephone Conversations...................................................... 2078Uchechukwu O. Ofoegbu, Ananth N. Iyer, Robert E. Yantorno, Stanley J. Wenndt

Improvement Speaker Clustering Using Global Similarity Features....................................... 2082Konstantin Biatov, Joachim Kohler

Voting for Two Speaker Segmentation ....................................................................................... 2086Balakrishnan Narayanaswamy, Rashmi Gangadharaiah, Richard M. Stern

Unsupervised Model Adaptation for Speaker Verification ....................................................... 2090Alexandre Preti, Jean-Francois Bonastre

A Quality Measure Method Using Gaussian Mixture Models and Divergence Measure for Speaker Identification ............................................................................................. 2094

Rong Zheng, Shuwu Zhang, Bo Xu

Gammatone Auditory Filterbank and Independent Component Analysis for Speaker Identification................................................................................................................... 2098

Yushi Zhang, Waleed H. Abdulla

Study on Speaker Verification on Emotional Speech ............................................................... 2102Wei Wu, Thomas Fang Zheng, Ming-Xing Xu, Huan-Jun Bao

On the Fusion of Prosody, Voice Spectrum and Face Features for Multimodal Person Verification ....................................................................................................................... 2106

M. Farrus, A. Garde, P. Ejarque, J. Luque, Javier Hernando

An MRI Based Study of the Acoustic Effects of Sinus Cavities and Its Application to Speaker Recognition ................................................................................................................ 2110

Tarun Pruthi, Carol Y. Espy-Wilson

Speaker Verification with Non-Audible Murmur Segments ...................................................... 2114Mariko Kojima, Tomoko Matsui, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano

Automatic Recognition of Speakers' Age and Gender on the Basis of Empirical Studies ........................................................................................................................................... 2118

Christian Muller

Text-Independent Speaker Identification in Birds ..................................................................... 2122E. J. S. Fox, J. D. Roberts, M. Bennamoun

Automatic Acoustic Identification of Insects Inspired by the Speaker Recognition Paradigm ........................................................................................................................................ 2126

Ilyas Potamitis, Todor Ganchev, Nikos Fakotakis

MULTICHANNEL SPEECH ENHANCEMENT/SPEECH PERCEPTION

Improved Hybrid Microphone Array Post-Filter by Integrating a Robust Speech Absence Probability Estimator for Speech Enhancement ....................................................... 2130

Junfeng Li, Masato Akagi, Yoiti Suzuki

Soft Decision Combining for Dual Channel Noise Reduction.................................................. 2134Timo Gerkmann, Rainer Martin

An Improved Affine Projection Algorithm Based Crosstalk Resistant Adaptive Noise Canceller ............................................................................................................................. 2138

Guo Chen, Vijay Parsa

An Optimum Microphone Array Post-Filter for Speech Applications ..................................... 2142Stamatis Leukimmiatis, Dimitrios Dimitriadis, Petros Maragos

Multi-Microphone Periodicity Function for Robust F0 Estimation in Real Noisy and Reverberant Environments................................................................................................... 2146

Federico Flego, Maurizio Omologo

A New Dual-Microphone Speech Enhancement Method for Oriented Noises........................ 2150H. R. Abutalebi, M. Pourahmadi, M. R. Aghabozorgi

50 Years Late: Repeating Miller-Nicely 1955 .............................................................................. 2154Andrew Lovitt, Jont B. Allen

New 20-Word Lists for Word Intelligibility Test in Japanese.................................................... 2158Shuichi Sakamoto, Tadahiro Yoshikawa, Shigeaki Amano, Yoiti Suzuki, Tadahisa Kondo

Sparseness and Speech Perception in Noise ............................................................................ 2162Guoping Li, Mark E. Lutman

An Assessment of Automatic Speech Recognition as Speech Intelligibility Estimation in the Context of Additive Noise .............................................................................. 2166

Wei M. Liu, John S. D. Mason, Nicholas W. D. Evans, Keith A. Jellyman

Underlying Quality Dimensions of Modern Telephone Connections ...................................... 2170Marcel Waltermann, Kirstin Scholz, Alexander Raake, Ulrich Heute, Sebastian Moller

An ERB Loudness Pattern Based Objective Speech Quality Measure ................................... 2174Guo Chen, Vijay Parsa, Susan Scollie

DIARIZATION IN ASR

A Spectral Clustering Approach to Speaker Diarization........................................................... 2178Huazhong Ning, Ming Liu, Hao Tang, Thomas S. Huang

BINSEG: An Efficient Speaker-Based Segmentation Technique ............................................. 2182Jindrich Zdansky

Multi-Stream Speaker Diarization Systems for the Meetings Domain..................................... 2186Ascension Gallardo-Antolin, Xavier Anguera, Chuck Wooters

Improved Performance Evaluation of Speech Event Detectors............................................... 2190Carla Lopes, Fernando Perdigao

Speaker Diarization for Multiple Distant Microphone Meetings: Mixing Acoustic Features and Inter-Channel Time Differences ........................................................................... 2194

Jose M. Pardo, Xavier Anguera, Chuck Wooters

Low-Complexity and Efficient Classification of Voiced/Unvoiced/Silence for Noisy Environments ................................................................................................................................ 2198

Tuan Van Pham, Gernot Kubin

LANGUAGE MODEL ADAPTATION, REFINEMENT, AND EVALUATION

Unsupervised Language Model Adaptation Based on Automatic Text Collection from WWW ..................................................................................................................................... 2202

Motoyuki Suzuki, Yasutomo Kajiura, Akinori Ito, Shozo Makino

Unsupervised Language Model Adaptation Using Latent Semantic Marginals ..................... 2206Yik-Cheung Tam, Tanja Schultz

Unsupervised Language Model Adaptation for Mandarin Broadcast Conversation Transcription ................................................................................................................................. 2210

David Mrva, Philip C. Woodland

Language Model Adaptation for Tiny Adaptation Corpora....................................................... 2214Dietrich Klakow

Pronunciation Dependent Language Models............................................................................. 2218Andrej Ljolje

Improving Perplexity Measures to Incorporate Acoustic Confusability ................................. 2222Amit Anil Nanavati, Nitendra Rajput

SPEECH PRODUCTION, PHYSIOLOGY, AND PATHOLOGY II

Voice Source Correlates of Prosodic Features in American English: A Pilot Study ............. 2226Markus Iseli, Yen-Liang Shue, Melissa A. Epstein, Patricia Keating, Jody Kreiman, Abeer Alwan

On Speech Variation and Word Type Differentiation by Articulatory Feature Representations ............................................................................................................................ 2230

Louis Ten Bosch, R. Harald Baayen, Mirjam Ernestus

A Study of Emotional Speech Articulation Using a Fast Magnetic Resonance Imaging Technique ....................................................................................................................... 2234

Sungbok Lee, Erik Bresch, Jason Adams, Abe Kazemzadeh, Shrikanth Narayanan

Reconstructing Tongue Movements from Audio and Video .................................................... 2238Hedvig Kjellstrom, Olov Engwall, Olle Balter

New Considerations for Vowel Nasalization Based on Separate Mouth-Nose Recording ...................................................................................................................................... 2242

Gang Feng, Cyril Kotenkoff

An Acoustic and Articulatory Study of Lombard Speech: Global Effects on the Utterance........................................................................................................................................ 2246

Maeva Garnier, Lucie Bailly, Marion Dohen, Pauline Welby, Helene Loevenbruck

VOICE MORPHING

Improving the Performance of HMM-Based Voice Conversion Using Context Clustering Decision Tree and Appropriate Regression Matrix Format ................................... 2250

Long Qin, Yi-Jian Wu, Zhen-Hua Ling, Ren-Hua Wang

Map-Based Adaptation for Speech Conversion Using Adaptation Data Selection and Non-Parallel Training ............................................................................................................ 2254

Chung-Han Lee, Chung-Hsien Wu

Novel Method for Data Clustering and Mode Selection with Application in Voice Conversion .................................................................................................................................... 2258

Jani Nurminen, Jilei Tian, Victor Popa

Text-Independent Cross-Language Voice Conversion ............................................................. 2262David Sundermann, Harald Hoge, Antonio Bonafonte, Hermann Ney, Julia Hirschberg

Maximum Likelihood Voice Conversion Based on GMM with STRAIGHT Mixed Excitation ....................................................................................................................................... 2266

Yamato Ohtani, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano

Improving Body Transmitted Unvoiced Speech with Statistical Voice Conversion .............. 2270Mikihiro Nakagiri, Tomoki Toda, Hideki Kashioka, Kiyohiro Shikano

An HMM-Based Singing Voice Synthesis System..................................................................... 2274Keijiro Saino, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

Voice Conversion Based on Mixtures of Factor Analyzers ...................................................... 2278Yosuke Uto, Yoshihiko Nankaku, Tomoki Toda, Akinobu Lee, Keiichi Tokuda

Efficient Gaussian Mixture Model Evaluation in Voice Conversion ........................................ 2282Jilei Tian, Jani Nurminen, Victor Popa

Constrained Structural Maximum a posteriori Linear Regression for Average-Voice-Based Speech Synthesis................................................................................................... 2286

Yuji Nakano, Makoto Tachibana, Junichi Yamagishi, Takao Kobayashi

Frequency Warping Based on Mapping Formant Parameters ................................................. 2290Zhi-Wei Shuang, Raimo Bakis, Slava Shechtman, Dan Chazan, Yong Qin

Automatic Phonetic Segmentation by Using a SPM-Based Approach for a Mandarin Singing Voice Corpus.................................................................................................. 2294

Cheng-Yuan Lin, J.-S. Roger Jang

A Comparison of Singing Evaluation Algorithms ..................................................................... 2298Partha Lal

ASR OTHER II

Improving Speech Recognition of Two Simultaneous Speech Signals by Integrating ICA BSS and Automatic Missing Feature Mask Generation ................................. 2302

Ryu Takeda, Shun'Ichi Yamamoto, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

Missing-Feature Reconstruction for Band-Limited Speech Recognition in Spoken Document Retrieval ...................................................................................................................... 2306

Wooil Kim, John H. L. Hansen

Incremental Learning of MAP Context-Dependent Edit Operations for Spoken Phone Number Recognition in an Embedded Platform ............................................................ 2310

Hahn Koo, Yan Ming Cheng

Development and Evaluation of Speech Database in Automotive Environments for Practical Speech Recognition Systems................................................................................ 2314

Yasunari Obuchi, Nobuo Hataoka

An Effective and Efficient Utterance Verification Technology Using Word N-Gram Filler Models .................................................................................................................................. 2318

Dong Yu, Yun-Cheng Ju, Alex Acero

An Efficient Bispectrum Phase Entropy-Based Algorithm for VAD ........................................ 2322J. M. Gorriz, Javier Ramirez, C. G. Puntonet, Jose C. Segura

Two-Step Unsupervised Speaker Adaptation Based on Speaker and Gender Recognition and HMM Combination ........................................................................................... 2326

Petr Cerva, Jan Nouza, Jan Silovsky

CENSREC2: Corpus and Evaluation Environments for In Car Continuous Digit Speech Recognition...................................................................................................................... 2330

Satoshi Nakamura, Masakiyo Fujimoto, Kazuya Takeda

Detection of Word Fragments in Mandarin Telephone Conversation ..................................... 2334Cheng-Tao Chu, Yun-Hsuan Sung, Yuan Zhao, Daniel Jurafsky

A DTW-Based Dissimilarity Measure for Left-to-Right Hidden Markov Models and Its Application to Word Confusability Analysis ......................................................................... 2338

Qiang Huo, Wei Li

Multi-Flow Block Interleaving Applied to Distributed Speech Recognition Over IP Networks ........................................................................................................................................ 2342

Angel M. Gomez, Juan J. Ramos-Munoz, Antonio M. Peinado, Victoria Sanchez

Moving Speech Recognition from Software to Silicon: The In Silico Vox Project................. 2346Edward C. Lin, Kai Yu, Rob A. Rutenbar, Tsuhan Chen

A Study on Detection Based Automatic Speech Recognition ................................................. 2350Chengyuan Ma, Yu Tsao, Chin-Hui Lee

Novel Time Domain Multi-Class SVMs for Landmark Detection .............................................. 2354Rahul Chitturi, Mark Hasegawa Johnson

PROSODY

Towards Automatic Parameter Extraction of Command-Response Model for Cantonese ...................................................................................................................................... 2358

Raymond W. M. Ng, Tan Lee, Wentao Gu

A Model for the f0 Reset in Corpus-Based Intonation Approaches ........................................ 2362Francisco Campillo, Jan P. H. Van Santen, Eduardo R. Banga

Generating German Intonation with a Trainable Prosodic Model............................................ 2366Gerard Bailly, Jan Gorisch

Incorporating Second-Order Information into Two-Step Major Phrase Break Prediction for Korean ................................................................................................................... 2370

Seungwon Kim, Jinsik Lee, Byeongchang Kim, Gary Geunbae Lee

Totally Data-Driven Duration Modeling Based on Generalized Linear Model for Mandarin TTS ................................................................................................................................ 2374

Lifu Yi, Jian Li, Xiaoyan Lou, Jie Hao

Segmental Duration Modeling in Turkish ................................................................................... 2378Ozlem Ozturk, Tolga Ciloglu

Lexical Stress in Continuous Speech Recognition ................................................................... 2382Rogier C. Van Dalen, Pascal Wiggers, Leon J. M. Rothkrantz

Improving Tone Recognition with Combined Frequency and Amplitude Modelling ............. 2386Siwei Wang, Gina-Anne Levow

Latent Prosodic Modeling (LPM) for Speech with Applications in Recognizing Spontaneous Mandarin Speech with Disfluencies.................................................................... 2390

Che-Kuang Lin, Lin-Shan Lee

Tone Recognition of Continuous Speech of Standard Chinese Using Neural Network and Tone Nucleus Model .............................................................................................. 2394

Keikichi Hirose, Hui Hu, Xiaodong Wang, Nobuaki Minematsu

Prosodic Feature Generation for Back-Channel Prediction ..................................................... 2398Thamar Solorio, Olac Fuentes, Nigel G. Ward, Yaffa Al Bayyari

On the Sufficiency and Redundancy of Pitch for TRP Projection ........................................... 2402Wieneke Wesseling, R. J. J. H. Van Son, Louis C. W. Pols

DISCRIMINATIVE TRAINING

Hypothesis Spaces for Minimum Bayes Risk Training in Large Vocabulary Speech Recognition...................................................................................................................... 2406

Matthew Gibson, Thomas Hain

Minimum Divergence Based Discriminative Training ............................................................... 2410Jun Du, Peng Liu, Frank K. Soong, Jian-Lai Zhou, Ren-Hua Wang

Solving Large Margin Estimation of HMMS via Semidefinite Programming .......................... 2414Xinwei Li, Hui Jiang

Use of Incrementally Regulated Discriminative Margins in MCE Training for Speech Recognition...................................................................................................................... 2418

Dong Yu, Li Deng, Xiaodong He, Alex Acero

Soft Margin Estimation of Hidden Markov Model Parameters ................................................. 2422Jinyu Li, Ming Yuan, Chin-Hui Lee

Discriminative Models for Spoken Language Understanding.................................................. 2426Ye-Yi Wang, Alex Acero

SPEECH SYNTHESIS

Evaluating a Virtual Speech Cuer................................................................................................ 2430G. Gibert, Gerard Bailly, F. Elisei

Intelligibility of Machine Translation Output in Speech Synthesis.......................................... 2434Laura Mayfield Tomokiyo, Kay Peterson, Alan W. Black, Kevin A. Lenzo

A Technique for Controlling Voice Quality of Synthetic Speech Using Multiple Regression HSMM......................................................................................................................... 2438

Makoto Tachibana, Takashi Nose, Junichi Yamagishi, Takao Kobayashi

Learning from Errors in Grapheme-to-Phoneme Conversion .................................................. 2442Tatyana Polyakova, Antonio Bonafonte

Eigenvoice Conversion Based on Gaussian Mixture Model .................................................... 2446Tomoki Toda, Yamato Ohtani, Kiyohiro Shikano

Generating Time-Constrained Audio Presentations of Structured Information..................... 2450Brian Langner, Rohit Kumar, Arthur Chan, Lingyun Gu, Alan W. Black

MULTIMODAL PROCESSING

Multimodal Authentication Using Qualitative Support Vector Machines................................ 2454F. Alsaade, A. Ariyaeeinia, L. Meng, A. Malegaonkar

Adaptive Multimodal Fusion by Uncertainty Compensation.................................................... 2458Vassilis Pitsikalis, Athanassios Katsamanis, George Papandreou, Petros Maragos

Effects of Familiarity with Faces and Voices on Second-Language Speech Processing: Components of Memory Traces............................................................................. 2462

Debra M. Hardison

Automatic Metadata Generation and Video Editing Based on Speech and Image Recognition for Medical Education Contents ............................................................................ 2466

Satoshi Tamura, Koji Hashimoto, Jiong Zhu, Satoru Hayamizu, Hirotsugu Asai, Hideki Tanahashi, Makoto Kanagawa

Analysis of Correlation Between Audio and Visual Speech Features for Clean Audio Feature Prediction in Noise .............................................................................................. 2470

Ibrahim Almajai, Ben Milner, Jonathan Darch

TDA: A New Trainable Trajectory Formation System for Facial Animation............................ 2474Oxana Govokhina, Gerard Bailly, Gaspard Breton, Paul Bagshaw

SPEECH ANALYSIS

Modeling of Speech Signals Based on Bessel-Like Orthogonal Transform .......................... 2478Giorgio Biagetti, Paolo Crippa, Claudio Turchetti

Glottal Closure and Opening Detection for Flexible Parametric Voice Coding...................... 2482Pamornpol Jinachitra

Independent Components for Acoustic Modeling..................................................................... 2486Jan Trmal, Jan Vanek, Ludek Muller, Jan Zelinka

Pitch-Scale Modification Using the Modulated Aspiration Noise Source............................... 2490Daryush Mehta, Thomas F. Quatieri

Max-Gabor Analysis and Synthesis of Spectrograms .............................................................. 2494Tony Ezzat, Jake Bouvrie, Tomaso Poggio

Monitoring of the Natural Voice Variations in Open and Closed Phases with Frequency Warped ARMA Modeling ........................................................................................... 2498

Pedro J. Quintana-Morales, Juan L. Navarro-Mesa, Antonio G. Ravelo-Garcia, Fernando D. Lorenzo-Garcia

Speech Analyzer Using a Joint Estimation Model of Spectral Envelope and Fine Structure ........................................................................................................................................ 2502

Hirokazu Kameoka, Jonathan Le Roux, Nobutaka Ono, Shigeki Sagayama

An Investigation of Manifold Learning for Speech Analysis .................................................... 2506Andrew Errity, John McKenna

An Incremental Algorithm for Signal Reconstruction from Short-Time Fourier Transform Magnitude ................................................................................................................... 2510

Jake Bouvrie, Tony Ezzat

Automatic Assignment of Anchoring Points on Vowel Templates for Defining Correspondence Between Time-Frequency Representations of Speech Samples ............... 2514

Toru Takahashi, Masashi Nishi, Toshio Irino, Hideki Kawahara

Nonlinear Dynamical Invariants for Speech Recognition......................................................... 2518S. Prasad, S. Srinivasan, M. Pannuri, G. Lazarou, Joseph Picone

ADVANCES IN NOISY ASR

Exploiting Polynomial-Fit Histogram Equalization and Temporal Average for Robust Speech Recognition ........................................................................................................ 2522

Shih-Hsiang Lin, Yao-Ming Yeh, Berlin Chen

Missing Data Mask Models with Global Frequency and Temporal Constraints..................... 2526Sebastien Demange, Christophe Cerisara, Jean-Paul Haton

Multi-Stream ASR: An Oracle Perspective ................................................................................. 2530Hemant Misra, Jithendra Vepa, Herve Bourlard

A Weight Estimation Method Using LDA for Multi-Band Speech Recognition ...................... 2534Koji Iwano, Kaname Kojima, Sadaoki Furui

Powered Cepstral Normalization (P-CN) for Robust Features in Speech Recognition ................................................................................................................................... 2538

Chang-Wen Hsu, Lin-Shan Lee

Robust Automatic Speech Recognition for Accented Mandarin in Car Environments ................................................................................................................................ 2542

Pei Ding, Lei He, Xiang Yan, Jie Hao

A Robust Feature Extraction Based on the MTF Concept for Speech Recognition in Reverberant Environment ........................................................................................................ 2546

Xugang Lu, Masashi Unoki, Masato Akagi

Clean Speech Feature Estimation Based on Soft Spectral Masking ....................................... 2550Young Joon Kim, Woohyung Lim, Nam Soo Kim

Robust Speech Recognition by Modifying Clean and Telephone Feature Vectors Using Bidirectional Neural Network............................................................................................ 2554

Mansoor Vali, Seyyed Ali Seyyed Salehi, Kazem Karimi

Silence Energy Normalization for Robust Speech Recognition in Additive Noise Environment .................................................................................................................................. 2558

Chung-Fu Tai, Jeih-Weih Hung

Handling Convolutional Noise in Missing Data Automatic Speech Recognition................... 2562Maarten Van Segbroeck, Hugo Van Hamme

Noisy Speech Recognition Based on Selection of Multiple Noise Suppression Methods Using Noise GMMs........................................................................................................ 2566

Norihide Kitaoka, Souta Hamaguchi, Seiichi Nakagawa

Using Posterior-Based Features in Template Matching for Speech Recognition ................. 2570Guillermo Aradilla, Jithendra Vepa, Herve Bourlard

Hypothesis-Based Feature Combination of Multiple Speech Inputs for Robust Speech Recognition in Automotive Environments ................................................................... 2574

Yasunari Obuchi, Nobuo Hataoka

SOURCE SEPARATION AND LOCALIZATION

Continuous Time-Frequency Masking Method for Blind Speech Separation with Adaptive Choice of Threshold Parameter Using ICA ................................................................ 2578

Zbynek Koldovsky, Jan Nouza, Jan Kolorenc

Multistage Convolutive Blind Source Separation for Speech Mixture .................................... 2582Yanxue Liang, Ichiro Hagiwara

Detection and Separation of Speech Events in Meeting Recordings...................................... 2586Futoshi Asano, Jun Ogata

Audio Person Tracking in a Smart-Room Environment............................................................ 2590Alberto Abad, Carlos Segura, Dusan Macho, Javier Hernando, Climent Nadeu

Tracking and Beamforming for Multiple Simultaneous Speakers with Probabilistic Data Association Filters ............................................................................................................... 2594

Tobias Gehrig, Ulrich Klee, John W. McDonough, Shajith Ikbal, Matthias Wolfel, Christian Fugen

Modeling the Precedence Effect for Binaural Sound Source Localization in Noisy and Echoic Environments ............................................................................................................ 2598

Martin Heckmann, Tobias Rodemann, Bjorn Scholling, Frank Joublin, Christian Goerick

Using a Differential Microphone Array to Estimate the Direction of Arrival of Two Acoustic Sources.......................................................................................................................... 2602

Fotios Talantzis, Anthony G. Constantinides, Lazaros C. Polymenakos

Speaker Localization Based on Oriented Global Coherence Field.......................................... 2606Alessio Brutti, Maurizio Omologo, Piergiorgio Svaizer

Performance Evaluation of Three Features for Model-Based Single Channel Speech Separation Problem ........................................................................................................ 2610

M. H. Radfar, R. M. Dansereau, A. Sayadiyan

Single-Channel Speech Separation Using Sparse Non-Negative Matrix Factorization .................................................................................................................................. 2614

Mikkel N. Schmidt, Rasmus K. Olsson

Adaptive Speech Enhancement for Speech Separation in Diffuse Noise............................... 2618Rong Hu, Yunxin Zhao

A Probabilistic Graphical Model for Microphone Array Source Separation Using Rich Pre-Trained Source Models................................................................................................. 2622

H. T. Attias

Geometrically Constrained Permutation-Free Source Separation in an Undercomplete Speech Unmixing Scenario .............................................................................. 2626

Erik Visser

Highly Directional Multi-Beam Audio Loudspeaker .................................................................. 2630Dirk Olszewski, Klaus Linhard

Author Index