INTERSPEECH 2005: Lisbon, Portugal

Keynote Papers

• Graeme M. Clark:
  The multiple-channel cochlear implant: interfacing electronic technology to human consciousness. 1-4
  

Speech Recognition - Language Modelling I-III

• Yik-Cheung Tam, Tanja Schultz:
  Dynamic language model adaptation using variational Bayes inference. 5-8
  
• Vidura Seneviratne, Steve Young:
  The hidden vector state language model. 9-12
  
• Shinsuke Mori, Gakuto Kurata:
  Class-based variable memory length Markov model. 13-16
  
• Alexander Gruenstein, Chao Wang, Stephanie Seneff:
  Context-sensitive statistical language modeling. 17-20
  
• Chao Wang, Stephanie Seneff, Grace Chung:
  Language model data filtering via user simulation and dialogue resynthesis. 21-24
  
• Jen-Tzung Chien, Meng-Sung Wu, Chia-Sheng Wu:
  Bayesian learning for latent semantic analysis. 25-28
  

Prosody in Language Performance I, II

• Daniel Hirst, Caroline Bouzon:
  The effect of stress and boundaries on segmental duration in a corpus of authentic speech (british English). 29-32
  
• Tomoko Ohsuga, Masafumi Nishida, Yasuo Horiuchi, Akira Ichikawa:
  Investigation of the relationship between turn-taking and prosodic features in spontaneous dialogue. 33-36
  
• Michiko Watanabe, Keikichi Hirose, Yasuharu Den, Nobuaki Minematsu:
  Filled pauses as cues to the complexity of following phrases. 37-40
  
• Katrin Schneider, Bernd Möbius:
  Perceptual magnet effect in German boundary tones. 41-44
  
• Angela Grimm, Jochen Trommer:
  Constraints on the acquisition of simplex and complex words in German. 45-48
  
• Julien Meyer:
  Whistled speech: a natural phonetic description of languages adapted to human perception and to the acoustical environment. 49-52
  

Spoken Language Extraction / Retrieval I, II

• Olivier Siohan, Michiel Bacchiani:
  Fast vocabulary-independent audio search using path-based graph indexing. 53-56
  
• John Makhoul, Alex Baron, Ivan Bulyko, Long Nguyen, Lance A. Ramshaw, David Stallard, Richard M. Schwartz, Bing Xiang:
  The effects of speech recognition and punctuation on information extraction performance. 57-60
  
• Ciprian Chelba, Alex Acero:
  Indexing uncertainty for spoken document search. 61-64
  
• Tomoyosi Akiba, Hiroyuki Abe:
  Exploiting passage retrieval for n-best rescoring of spoken questions. 65-68
  
• BalaKrishna Kolluru, Heidi Christensen, Yoshihiko Gotoh:
  Multi-stage compaction approach to broadcast news summarisation. 69-72
  
• Chien-Lin Huang, Chia-Hsin Hsieh, Chung-Hsien Wu:
  Audio-video summarization of TV news using speech recognition and shot change detection. 73-76
  

The Blizzard Challenge 2005

• Alan W. Black, Keiichi Tokuda:
  The blizzard challenge - 2005: evaluating corpus-based speech synthesis on common datasets. 77-80
  
• Shinsuke Sakai, Han Shu:
  A probabilistic approach to unit selection for corpus-based speech synthesis. 81-84
  
• John Kominek, Christina L. Bennett, Brian Langner, Arthur R. Toth:
  The blizzard challenge 2005 CMU entry - a method for improving speech synthesis systems. 85-88
  
• H. Timothy Bunnell, Christopher A. Pennington, Debra Yarrington, John Gray:
  Automatic personal synthetic voice construction. 89-92
  
• Heiga Zen, Tomoki Toda:
  An overview of nitech HMM-based speech synthesis system for blizzard challenge 2005. 93-96
  
• Wael Hamza, Raimo Bakis, Zhiwei Shuang, Heiga Zen:
  On building a concatenative speech synthesis system from the blizzard challenge speech databases. 97-100
  
• Robert A. J. Clark, Korin Richmond, Simon King:
  Multisyn voices from ARCTIC data for the blizzard challenge. 101-104
  
• Christina L. Bennett:
  Large scale evaluation of corpus-based synthesizers: results and lessons from the blizzard challenge 2005. 105-108
  

New Applications

• Berlin Chen, Yi-Ting Chen, Chih-Hao Chang, Hung-Bin Chen:
  Speech retrieval of Mandarin broadcast news via mobile devices. 109-112
  
• Michiaki Katoh, Kiyoshi Yamamoto, Jun Ogata, Takashi Yoshimura, Futoshi Asano, Hideki Asoh, Nobuhiko Kitawaki:
  State estimation of meetings by information fusion using Bayesian network. 113-116
  
• Roger K. Moore:
  Results from a survey of attendees at ASRU 1997 and 2003. 117-120
  
• Reinhold Haeb-Umbach, Basilis Kladis, Joerg Schmalenstroeer:
  Speech processing in the networked home environment - a view on the amigo project. 121-124
  
• Masahide Sugiyama:
  Fixed distortion segmentation in efficient sound segment searching. 125-128
  
• Tin Lay Nwe, Haizhou Li:
  Identifying singers of popular songs. 129-132
  
• Jun Ogata, Masataka Goto:
  Speech repair: quick error correction just by using selection operation for speech input interfaces. 133-136
  
• Dirk Olszewski, Fransiskus Prasetyo, Klaus Linhard:
  Steerable highly directional audio beam loudspeaker. 137-140
  
• Hassan Ezzaidi, Jean Rouat:
  Automatic music genre classification using second-order statistical measures for the prescriptive approach. 141-144
  
• Alberto Abad, Dusan Macho, Carlos Segura, Javier Hernando, Climent Nadeu:
  Effect of head orientation on the speaker localization performance in smart-room environment. 145-148
  
• Corinne Fredouille, Gilles Pouchoulin, Jean-François Bonastre, M. Azzarello, Antoine Giovanni, Alain Ghio:
  Application of automatic speaker recognition techniques to pathological voice assessment (dysphonia). 149-152
  
• Upendra V. Chaudhari, Ganesh N. Ramaswamy, Eddie Epstein, Sasha Caskey, Mohamed Kamal Omar:
  Adaptive speech analytics: system, infrastructure, and behavior. 153-156
  

E-learning and Spoken Language Processing

• Katherine Forbes-Riley, Diane J. Litman:
  Correlating student acoustic-prosodic profiles with student learning in spoken tutoring dialogues. 157-160
  
• Diane J. Litman, Katherine Forbes-Riley:
  Speech recognition performance and learning in spoken dialogue tutoring. 161-164
  
• Satoshi Asakawa, Nobuaki Minematsu, Toshiko Isei-Jaakkola, Keikichi Hirose:
  Structural representation of the non-native pronunciations. 165-168
  
• Fu-Chiang Chou:
  Ya-ya language box - a portable device for English pronunciation training with speech recognition technologies. 169-172
  
• Akinori Ito, Yen-Ling Lim, Motoyuki Suzuki, Shozo Makino:
  Pronunciation error detection method based on error rule clustering using a decision tree. 173-176
  
• Abhinav Sethy, Shrikanth Narayanan, Nicolaus Mote, W. Lewis Johnson:
  Modeling and automating detection of errors in Arabic language learner speech. 177-180
  
• Felicia Zhang, Michael Wagner:
  Effects of F0 feedback on the learning of Chinese tones by native speakers of English. 181-184
  

E-inclusion and Spoken Language Processing I, II

• Tom Brøndsted, Erik Aaskoven:
  Voice-controlled internet browsing for motor-handicapped users. design and implementation issues. 185-188
  
• Briony Williams, Delyth Prys, Ailbhe Ní Chasaide:
  Creating an ongoing research capability in speech technology for two minority languages: experiences from the WISPR project. 189-192
  
• Anestis Vovos, Basilis Kladis, Nikolaos D. Fakotakis:
  Speech operated smart-home control system for users with special needs. 193-196
  
• Takatoshi Jitsuhiro, Shigeki Matsuda, Yutaka Ashikari, Satoshi Nakamura, Ikuko Eguchi Yairi, Seiji Igi:
  Spoken dialog system and its evaluation of geographic information system for elderly persons' mobility support. 197-200
  
• Daniele Falavigna, Toni Giorgino, Roberto Gretter:
  A frame based spoken dialog system for home care. 201-204
  

Acoustic Processing for ASR I-III

• Matthias Wölfel:
  Frame based model order selection of spectral envelopes. 205-208
  
• Vivek Tyagi, Christian Wellekens, Hervé Bourlard:
  On variable-scale piecewise stationary spectral analysis of speech signals for ASR. 209-212
  
• Arlo Faria, David Gelbart:
  Efficient pitch-based estimation of VTLN warp factors. 213-216
  
• Yanli Zheng, Richard Sproat, Liang Gu, Izhak Shafran, Haolang Zhou, Yi Su, Daniel Jurafsky, Rebecca Starr, Su-Youn Yoon:
  Accent detection and speech recognition for Shanghai-accented Mandarin. 217-220
  
• Loic Barrault, Renato de Mori, Roberto Gemello, Franco Mana, Driss Matrouf:
  Variability of automatic speech recognition systems using different features. 221-224
  
• Slavomír Lihan, Jozef Juhar, Anton Cizmar:
  Crosslingual and bilingual speech recognition with Slovak and Czech speechdat-e databases. 225-228
  
• Carmen Peláez-Moreno, Qifeng Zhu, Barry Y. Chen, Nelson Morgan:
  Automatic data selection for MLP-based feature extraction for ASR. 229-232
  
• Thilo Köhler, Christian Fügen, Sebastian Stüker, Alex Waibel:
  Rapid porting of ASR-systems to mobile devices. 233-236
  
• Hugo Meinedo, João Paulo Neto:
  A stream-based audio segmentation, classification and clustering pre-processing system for broadcast news using ANN models. 237-240
  
• Etienne Marcheret, Karthik Visweswariah, Gerasimos Potamianos:
  Speech activity detection fusing acoustic phonetic and energy features. 241-244
  
• Zoltán Tüske, Péter Mihajlik, Zoltán Tobler, Tibor Fegyó:
  Robust voice activity detection based on the entropy of noise-suppressed spectrum. 245-248
  
• Masamitsu Murase, Shun'ichi Yamamoto, Jean-Marc Valin, Kazuhiro Nakadai, Kentaro Yamada, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno:
  Multiple moving speaker tracking by microphone array on mobile robot. 249-252
  

Speech Recognition - Adaptation I, II

• Yaxin Zhang, Bian Wu, Xiaolin Ren, Xin He:
  A speaker biased SI recognizer for embedded mobile applications. 253-256
  
• Bart Bakker, Carsten Meyer, Xavier L. Aubert:
  Fast unsupervised speaker adaptation through a discriminative eigen-MLLR algorithm. 257-260
  
• Rusheng Hu, Jian Xue, Yunxin Zhao:
  Incremental largest margin linear regression and MAP adaptation for speech separation in telemedicine applications. 261-264
  
• Giulia Garau, Steve Renals, Thomas Hain:
  Applying vocal tract length normalization to meeting recordings. 265-268
  
• S. Umesh, András Zolnay, Hermann Ney:
  Implementing frequency-warping and VTLN through linear transformation of conventional MFCC. 269-272
  
• Xiaodong Cui, Abeer Alwan:
  MLLR-like speaker adaptation based on linearization of VTLN with MFCC features. 273-276
  
• Chandra Kant Raut, Takuya Nishimoto, Shigeki Sagayama:
  Model adaptation by state splitting of HMM for long reverberation. 277-280
  
• Daben Liu, Daniel Kiecza, Amit Srivastava, Francis Kubala:
  Online speaker adaptation and tracking for real-time speech recognition. 281-284
  
• Masafumi Nishida, Yasuo Horiuchi, Akira Ichikawa:
  Automatic speech recognition based on adaptation and clustering using temporal-difference learning. 285-288
  
• Hui Ye, Steve Young:
  Improving the speech recognition performance of beginners in spoken conversational interaction for language learning. 289-292
  
• Randy Gomez, Akinobu Lee, Hiroshi Saruwatari, Kiyohiro Shikano:
  Rapid unsupervised speaker adaptation based on multi-template HMM sufficient statistics in noisy environments. 293-296
  
• Dong-jin Choi, Yung-Hwan Oh:
  Rapid speaker adaptation for continuous speech recognition using merging eigenvoices. 297-300
  

Signal Analysis, Processing and Feature Estimation I-III

• Jian Liu, Thomas Fang Zheng, Jing Deng, Wenhu Wu:
  Real-time pitch tracking based on combined SMDSF. 301-304
  
• András Bánhalmi, Kornél Kovács, András Kocsor, László Tóth:
  Fundamental frequency estimation by least-squares harmonic model fitting. 305-308
  
• Siu Wa Lee, Frank K. Soong, Pak-Chung Ching:
  Harmonic filtering for joint estimation of pitch and voiced source with single-microphone input. 309-312
  
• Marián Képesi, Luis Weruaga:
  High-resolution noise-robust spectral-based pitch estimation. 313-316
  
• John-Paul Hosom:
  F0 estimation for adult and children's speech. 317-320
  
• Ben Milner, Xu Shao, Jonathan Darch:
  Fundamental frequency and voicing prediction from MFCCs for speech reconstruction from unconstrained speech. 321-324
  
• Nelly Barbot, Olivier Boëffard, Damien Lolive:
  F0 stylisation with a free-knot b-spline model and simulated-annealing optimization. 325-328
  
• Friedhelm R. Drepper:
  Voiced excitation as entrained primary response of a reconstructed glottal master oscillator. 329-332
  
• Damien Vincent, Olivier Rosec, Thierry Chonavel:
  Estimation of LF glottal source parameters based on an ARX model. 333-336
  
• Leigh D. Alsteris, Kuldip K. Paliwal:
  Some experiments on iterative reconstruction of speech from STFT phase and magnitude spectra. 337-340
  
• R. Muralishankar, Abhijeet Sangwan, Douglas D. O'Shaughnessy:
  Statistical properties of the warped discrete cosine transform cepstrum compared with MFCC. 341-344
  
• Aníbal J. S. Ferreira:
  New signal features for robust identification of isolated vowels. 345-348
  
• Jonathan Pincas, Philip J. B. Jackson:
  Amplitude modulation of frication noise by voicing saturates. 349-352
  
• Ron M. Hecht, Naftali Tishby:
  Extraction of relevant speech features using the information bottleneck method. 353-356
  
• Mohammad Firouzmand, Laurent Girin, Sylvain Marchand:
  Comparing several models for perceptual long-term modeling of amplitude and phase trajectories of sinusoidal speech. 357-360
  
• Hynek Hermansky, Petr Fousek:
  Multi-resolution RASTA filtering for TANDEM-based ASR. 361-364
  
• Woojay Jeon, Biing-Hwang Juang:
  A category-dependent feature selection method for speech signals. 365-368
  
• Trausti Kristjansson, Sabine Deligne, Peder A. Olsen:
  Voicing features for robust speech detection. 369-372
  

Robust Speech Recognition I-IV

• Svein Gunnar Pettersen, Magne Hallstein Johnsen, Tor André Myrvoll:
  Joint Bayesian predictive classification and parallel model combination for robust speech recognition. 373-376
  
• Glauco F. G. Yared, Fábio Violaro, Lívio C. Sousa:
  Gaussian elimination algorithm for HMM complexity reduction in continuous speech recognition systems. 377-380
  
• Luis Buera, Eduardo Lleida, Antonio Miguel, Alfonso Ortega:
  Robust speech recognition in cars using phoneme dependent multi-environment linear normalization. 381-384
  
• Yi Chen, Lin-Shan Lee:
  Energy-based frame selection for reliable feature normalization and transformation in robust speech recognition. 385-388
  
• Yoshitaka Nakajima, Hideki Kashioka, Kiyohiro Shikano, Nick Campbell:
  Remodeling of the sensor for non-audible murmur (NAM). 389-392
  
• Amarnag Subramanya, Jeff Bilmes, Chia-Ping Chen:
  Focused word segmentation for ASR. 393-396
  

Speech Perception I, II

• Jennifer A. Alexander, Patrick C. M. Wong, Ann R. Bradlow:
  Lexical tone perception in musicians and non-musicians. 397-400
  
• Joan K.-Y. Ma, Valter Ciocca, Tara L. Whitehill:
  Contextual effect on perception of lexical tones in Cantonese. 401-404
  
• Hansjörg Mixdorff, Yu Hu, Denis Burnham:
  Visual cues in Mandarin tone perception. 405-408
  
• Hansjörg Mixdorff, Yu Hu:
  Cross-language perception of word stress. 409-412
  
• Anne Cutler:
  The lexical statistics of word recognition problems caused by L2 phonetic confusion. 413-416
  
• Chun-Fang Huang, Masato Akagi:
  A multi-layer fuzzy logical model for emotional speech perception. 417-420
  

Spoken Language Understanding I, II

• Ian R. Lane, Tatsuya Kawahara:
  Utterance verification incorporating in-domain confidence and discourse coherence measures. 421-424
  
• Constantinos Boulis, Mari Ostendorf:
  Using symbolic prominence to help design feature subsets for topic classification and clustering of natural human-human conversations. 425-428
  
• Katsuhito Sudoh, Hajime Tsukada:
  Tightly integrated spoken language understanding using word-to-concept translation. 429-432
  
• Ruhi Sarikaya, Hong-Kwang Jeff Kuo, Vaibhava Goel, Yuqing Gao:
  Exploiting unlabeled data using multiple classifiers for improved natural language call-routing. 433-436
  
• Hong-Kwang Jeff Kuo, Vaibhava Goel:
  Active learning with minimum expected error for spoken language understanding. 437-440
  
• Matthias Thomae, Tibor Fábián, Robert Lieb, Günther Ruske:
  Lexical out-of-vocabulary models for one-stage speech interpretation. 441-444
  

E-inclusion and Spoken Language Processing I, II

• Mark S. Hawley, Phil Green, Pam Enderby, Stuart Cunningham, Roger K. Moore:
  Speech technology for e-inclusion of people with physical disabilities and disordered speech. 445-448
  
• Björn Granström:
  Speech technology for language training and e-inclusion. 449-452
  
• Roger Tucker, Ksenia Shalonova:
  Supporting the creation of TTS for local language voice information systems. 453-456
  
• Ove Andersen, Christian Hjulmand:
  Access for all - a talking internet service. 457-460
  
• Knut Kvale, Narada D. Warakagoda:
  A speech centric mobile multimodal service useful for dyslectics and aphasics. 461-464
  

Paralinguistic and Nonlinguistic Information in Speech

• Nick Campbell, Hideki Kashioka, Ryo Ohara:
  No laughing matter. 465-468
  
• Christophe Blouin, Valérie Maffiolo:
  A study on the automatic detection and characterization of emotion in a voice service context. 469-472
  
• Raul Fernandez, Rosalind W. Picard:
  Classical and novel discriminant features for affect recognition from speech. 473-476
  
• Jaroslaw Cichosz, Krzysztof Slot:
  Low-dimensional feature space derivation for emotion recognition. 477-480
  
• Carlos Toshinori Ishi, Hiroshi Ishiguro, Norihiro Hagita:
  Proposal of acoustic measures for automatic detection of vocal fry. 481-484
  
• Khiet P. Truong, David A. van Leeuwen:
  Automatic detection of laughter. 485-488
  
• Anton Batliner, Stefan Steidl, Christian Hacker, Elmar Nöth, Heinrich Niemann:
  Tales of tuning - prototyping for automatic classification of emotional user states. 489-492
  
• Iker Luengo, Eva Navas, Inmaculada Hernáez, Jon Sánchez:
  Automatic emotion recognition using prosodic parameters. 493-496
  
• Sungbok Lee, Serdar Yildirim, Abe Kazemzadeh, Shrikanth Narayanan:
  An articulatory study of emotional speech production. 497-500
  
• Gregor Hofer, Korin Richmond, Robert A. J. Clark:
  Informed blending of databases for emotional speech synthesis. 501-504
  
• Fabio Tesser, Piero Cosi, Carlo Drioli, Graziano Tisato:
  Emotional FESTIVAL-MBROLA TTS synthesis. 505-508
  
• Felix Burkhardt:
  Emofilt: the simulation of emotional speech by prosody-transformation. 509-512
  
• Andrew Rosenberg, Julia Hirschberg:
  Acoustic/prosodic and lexical correlates of charismatic speech. 513-516
  
• Yoko Greenberg, Minoru Tsuzaki, Hiroaki Kato, Yoshinori Sagisaka:
  Communicative speech synthesis using constituent word attributes. 517-520
  
• Angelika Braun, Matthias Katerbow:
  Emotions in dubbed speech: an intercultural approach with respect to F0. 521-524
  
• Nicolas Audibert, Véronique Aubergé, Albert Rilliard:
  The prosodic dimensions of emotion in speech: the relative weights of parameters. 525-528
  
• Susanne Schötz:
  Stimulus duration and type in perception of female and male speaker age. 529-532
  
• Cecilia Ovesdotter Alm, Richard Sproat:
  Perceptions of emotions in expressive storytelling. 533-536
  
• Hideki Kawahara, Alain de Cheveigné, Hideki Banno, Toru Takahashi, Toshio Irino:
  Nearly defect-free F0 trajectory extraction for expressive speech modifications based on STRAIGHT. 537-540
  
• Tomoko Yonezawa, Noriko Suzuki, Kenji Mase, Kiyoshi Kogure:
  Gradually changing expression of singing voice based on morphing. 541-544
  

Issues in Large Vocabulary Decoding

• I. Lee Hetherington:
  A multi-pass, dynamic-vocabulary approach to real-time, large-vocabulary speech recognition. 545-548
  
• George Saon, Daniel Povey, Geoffrey Zweig:
  Anatomy of an extremely fast LVCSR decoder. 549-552
  
• Dong Yu, Li Deng, Alex Acero:
  Evaluation of a long-contextual-Span hidden trajectory model and phonetic recognizer using a* lattice search. 553-556
  
• Takaaki Hori, Atsushi Nakamura:
  Generalized fast on-the-fly composition algorithm for WFST-based speech recognition. 557-560
  
• Hiroaki Nanjo, Teruhisa Misu, Tatsuya Kawahara:
  Minimum Bayes-risk decoding considering word significance for information retrieval system. 561-564
  
• Arthur Chan, Mosur Ravishankar, Alexander I. Rudnicky:
  On improvements to CI-based GMM selection. 565-568
  
• Dominique Massonié, Pascal Nocera, Georges Linares:
  Scalable language model look-ahead for LVCSR. 569-572
  
• Miroslav Novak:
  Memory efficient approximative lattice generation for grammar based decoding. 573-576
  
• Dong-Hoon Ahn, Su-Byeong Oh, Minhwa Chung:
  Improved semi-dynamic network decoding using WFSTs. 577-580
  
• Janne Pylkkönen:
  New pruning criteria for efficient decoding. 581-584
  
• Tibor Fábián, Robert Lieb, Günther Ruske, Matthias Thomae:
  A confidence-guided dynamic pruning approach - utilization of confidence measurement in speech recognition. 585-588
  

Spoken Language Extraction / Retrieval I, II

• Toru Taniguchi, Akishige Adachi, Shigeki Okawa, Masaaki Honda, Katsuhiko Shirai:
  Discrimination of speech, musical instruments and singing voices using the temporal patterns of sinusoidal segments in audio signals. 589-592
  
• Gabriel Murray, Steve Renals, Jean Carletta:
  Extractive summarization of meeting recordings. 593-596
  
• Arjan van Hessen, Jaap Hinke:
  IR-based classification of customer-agent phone calls. 597-600
  
• Benoît Favre, Frédéric Béchet, Pascal Nocera:
  Mining broadcast news data: robust information extraction from word lattices. 601-604
  
• Mikko Kurimo, Ville T. Turunen:
  To recover from speech recognition errors in spoken document retrieval. 605-608
  
• Edgar González, Jordi Turmo:
  Unsupervised clustering of spontaneous speech documents. 609-612
  
• Masahide Yamaguchi, Masaru Yamashita, Shoichi Matsunaga:
  Spectral cross-correlation features for audio indexing of broadcast news and meetings. 613-616
  
• Chiori Hori, Alex Waibel:
  Spontaneous speech consolidation for spoken language applications. 617-620
  
• Sameer Maskey, Julia Hirschberg:
  Comparing lexical, acoustic/prosodic, structural and discourse features for speech summarization. 621-624
  
• Te-Hsuan Li, Ming-Han Lee, Berlin Chen, Lin-Shan Lee:
  Hierarchical topic organization and visual presentation of spoken documents using probabilistic latent semantic analysis (PLSA) for efficient retrieval/browsing applications. 625-628
  
• Janez Zibert, France Mihelic, Jean-Pierre Martens, Hugo Meinedo, João Paulo Neto, Laura Docío Fernández, Carmen García-Mateo, Petr David, Jindrich Zdánský, Matús Pleva, Anton Cizmar, Andrej Zgank, Zdravko Kacic, Csaba Teleki, Klára Vicsi:
  The COST278 broadcast news segmentation and speaker clustering evaluation - overview, methodology, systems, results. 629-632
  
• Igor Szöke, Petr Schwarz, Pavel Matejka, Lukas Burget, Martin Karafiát, Michal Fapso, Jan Cernocký:
  Comparison of keyword spotting approaches for informal continuous speech. 633-636
  
• Teruhisa Misu, Tatsuya Kawahara:
  Dialogue strategy to clarify user's queries for document retrieval system with speech interface. 637-640
  
• Nicolas Moreau, Shan Jin, Thomas Sikora:
  Comparison of different phone-based spoken document retrieval methods with text and spoken queries. 641-644
  

Signal Analysis, Processing and Feature Estimation I-III

• Pedro Gómez Vilda, Francisco Díaz, Agustín Álvarez Marquina, Rafael Martínez, Victoria Rodellar, Roberto Fernández-Baíllo, Alberto Nieto, Francisco J. Fernandez:
  PCA of perturbation parameters in voice pathology detection. 645-648
  
• Anindya Sarkar, T. V. Sreenivas:
  Dynamic programming based segmentation approach to LSF matrix reconstruction. 649-652
  
• T. Nagarajan, Douglas D. O'Shaughnessy:
  Explicit segmentation of speech based on frequency-domain AR modeling. 653-656
  
• Petr Motlícek, Lukás Burget, Jan Cernocký:
  Non-parametric speaker turn segmentation of meeting data. 657-660
  
• Petri Korhonen, Unto K. Laine:
  Unsupervised segmentation of continuous speech using vector autoregressive time-frequency modeling errors. 661-664
  
• P. Vijayalakshmi, M. RamasubbaReddy:
  The analysis on band-limited hypernasal speech using group delay based formant extraction technique. 665-668
  
• Jindrich Zdánský, Jan Nouza:
  Detection of acoustic change-points in audio records via global BIC maximization and dynamic programming. 669-672
  
• Md. Khademul Islam Molla, Keikichi Hirose, Nobuaki Minematsu:
  Multi-band approach of audio source discrimination with empirical mode decomposition. 673-676
  
• Minoru Tsuzaki, Satomi Tanaka, Hiroaki Kato, Yoshinori Sagisaka:
  Application of auditory image model for speech event detection. 677-680
  
• José Anibal Arias:
  Unsupervised identification of speech segments using kernel methods for clustering. 681-684
  
• Georgios Evangelopoulos, Petros Maragos:
  Speech event detection using multiband modulation energy. 685-688
  
• John Kominek, Alan W. Black:
  Measuring unsupervised acoustic clustering through phoneme pair merge-and-split tests. 689-692
  
• Fabio Valente, Christian Wellekens:
  Variational Bayesian speaker change detection. 693-696
  
• Sarah Borys, Mark Hasegawa-Johnson:
  Distinctive feature based SVM discriminant features for improvements to phone recognition on telephone band speech. 697-700
  
• P. Vijayalakshmi, M. RamasubbaReddy:
  Detection of hypernasality using statistical pattern classifiers. 701-704
  
• Luis Weruaga, Marián Képesi:
  Self-organizing chirp-sensitive artificial auditory cortical model. 705-708
  
• Sotiris Karabetsos, Pirros Tsiakoulis, Stavroula-Evita Fotinea, Ioannis Dologlou:
  On the use of a decimative spectral estimation method based on eigenanalysis and SVD for formant and bandwidth tracking of speech signals. 709-712
  
• Alexei V. Ivanov, Marek Parfieniuk, Alexander A. Petrovsky:
  Frequency-domain auditory suppression modelling (FASM) - a WDFT-based anthropomorphic noise-robust feature extraction algorithm for speech recognition. 713-716
  

Keynote Papers

• Fernando C. N. Pereira:
  Linear models for structure prediction. 717-720
  

Speech Recognition - Language Modelling I-III

• Chuang-Hua Chueh, To-Chang Chien, Jen-Tzung Chien:
  Discriminative maximum entropy language model for speech recognition. 721-724
  
• Maximilian Bisani, Hermann Ney:
  Open vocabulary speech recognition with flat hybrid models. 725-728
  
• Minwoo Jeong, Jihyun Eun, Sangkeun Jung, Gary Geunbae Lee:
  An error-corrective language-model adaptation for automatic speech recognition. 729-732
  
• Shiuan-Sung Lin, François Yvon:
  Discriminative training of finite state decoding graphs. 733-736
  
• Holger Schwenk, Jean-Luc Gauvain:
  Building continuous space language models for transcribing european languages. 737-740
  
• Peng Xu, Lidia Mangu:
  Using random forest language models in the IBM RT-04 CTS system. 741-744
  

Spoken Language Acquisition, Development and Learning I, II

• Willemijn Heeren:
  Perceptual development of the duration cue in dutch /a-a: /. 745-748
  
• Hong You, Abeer Alwan, Abe Kazemzadeh, Shrikanth Narayanan:
  Pronunciation variations of Spanish-accented English spoken by young children. 749-752
  
• Willemijn Heeren:
  L2 development of quantity perception: dutch listeners learning Finnish /t-t: /. 753-756
  
• Claudio Zmarich, Serena Bonifacio:
  Phonetic inventories in Italian children aged 18-27 months: a longitudinal study. 757-760
  
• Hiroko Hirano, Goh Kawai:
  Pitch patterns of intonational phrases and intonational phrase groups in native and non-native speech. 761-764
  
• Rebecca Hincks:
  Measuring liveliness in presentation speech. 765-768
  

Multi-modal / Multi-media Processing I, II

• Nick Campbell:
  Non-verbal speech processing for a communicative agent. 769-772
  
• Stuart N. Wrigley, Guy J. Brown:
  Physiologically motivated audio-visual localisation and tracking. 773-776
  
• Jing Huang, Daniel Povey:
  Discriminatively trained features using fMPE for multi-stream audio-visual speech recognition. 777-780
  
• Graziano Tisato, Piero Cosi, Carlo Drioli, Fabio Tesser:
  INTERFACE: a new tool for building emotive/expressive talking heads. 781-784
  
• Pascual Ejarque, Javier Hernando:
  Variance reduction by using separate genuine- impostor statistics in multimodal biometrics. 785-788
  
• Volker Schubert, Stefan W. Hamerich:
  The dialog application metalanguage GDialogXML. 789-792
  
• Jonas Beskow, Mikael Nordenberg:
  Data-driven synthesis of expressive visual speech using an MPEG-4 talking head. 793-796
  
• Oytun Türk, Marc Schröder, Baris Bozkurt, Levent M. Arslan:
  Voice quality interpolation for emotional text-to-speech synthesis. 797-800
  
• Murtaza Bulut, Carlos Busso, Serdar Yildirim, Abe Kazemzadeh, Chul Min Lee, Sungbok Lee, Shrikanth Narayanan:
  Investigating the role of phoneme-level modifications in emotional speech resynthesis. 801-804
  
• Björn Schuller, Ronald Müller, Manfred K. Lang, Gerhard Rigoll:
  Speaker independent emotion recognition by early fusion of acoustic and linguistic features within ensembles. 805-808
  
• Jonghwa Kim, Elisabeth André, Matthias Rehm, Thurid Vogt, Johannes Wagner:
  Integrating information from speech and physiological signals to achieve emotional sensitivity. 809-812
  
• Ellen Douglas-Cowie, Laurence Devillers, Jean-Claude Martin, Roddy Cowie, Suzie Savvidou, Sarkis Abrilian, Cate Cox:
  Multimodal databases of everyday emotion: facing up to complexity. 813-816
  

Spoken / Multi-modal Dialogue Systems I, II

• Francisco Torres, Emilio Sanchis, Encarna Segarra:
  Learning of stochastic dialog models through a dialog simulation technique. 817-820
  
• Lesley-Ann Black, Michael F. McTear, Norman D. Black, Roy Harper, Michelle Lemon:
  Evaluating the DI@l-log system on a cohort of elderly, diabetic patients: results from a preliminary study. 821-824
  
• Pavel Král, Christophe Cerisara, Jana Klecková:
  Combination of classifiers for automatic recognition of dialog acts. 825-828
  
• Xiaojun Wu, Thomas Fang Zheng, Michael Brasser, Zhanjiang Song:
  Rapidly developing spoken Chinese dialogue systems with the d-ear SDS SDK. 829-832
  
• Daniela Oria, Akos Vetek:
  Robust algorithms and interaction strategies for voice spelling. 833-836
  
• Ioannis Toptsis, Axel Haasch, Sonja Hwel, Jannik Fritsch, Gernot A. Fink:
  Modality integration and dialog management for a robotic assistant. 837-840
  
• Norbert Reithinger, Daniel Sonntag:
  An integration framework for a mobile multimodal dialogue system accessing the semantic web. 841-844
  
• Ryuichi Nisimura, Akinobu Lee, Masashi Yamada, Kiyohiro Shikano:
  Operating a public spoken guidance system in real environment. 845-848
  
• Esa-Pekka Salonen, Markku Turunen, Jaakko Hakulinen, Leena Helin, Perttu Prusi, Anssi Kainulainen:
  Distributed dialogue management for smart terminal devices. 849-852
  
• Jaakko Hakulinen, Markku Turunen, Esa-Pekka Salonen:
  Visualization of spoken dialogue systems for demonstration, debugging and tutoring. 853-856
  
• César González Ferreras, Valentín Cardeñoso-Payo:
  Development and evaluation of a spoken dialog system to access a newspaper web site. 857-860
  
• Olivier Pietquin, Richard Beaufort:
  Comparing ASR modeling methods for spoken dialogue simulation and optimal strategy learning. 861-864
  
• Shiu-Wah Chu, Ian M. O'Neill, Philip Hanna, Michael F. McTear:
  An approach to multi-strategy dialogue management. 865-868
  
• Anna Hjalmarsson:
  Towards user modelling in conversational dialogue systems: a qualitative study of the dynamics of dialogue parameters. 869-872
  
• Kouichi Katsurada, Kazumine Aoki, Hirobumi Yamada, Tsuneo Nitta:
  Reducing the description amount in authoring MMI applications. 873-876
  
• Kazunori Komatani, Naoyuki Kanda, Tetsuya Ogata, Hiroshi G. Okuno:
  Contextual constraints based on dialogue models in database search task for spoken dialogue systems. 877-880
  
• Mihai Rotaru, Diane J. Litman:
  Using word-level pitch features to better predict student emotions during spoken tutoring dialogues. 881-884
  
• Antoine Raux, Brian Langner, Dan Bohus, Alan W. Black, Maxine Eskenazi:
  Let's go public! taking a spoken dialog system to the real world. 885-888
  
• Shinya Fujie, Kenta Fukushima, Tetsunori Kobayashi:
  Back-channel feedback generation using linguistic and nonlinguistic information and its application to spoken dialogue system. 889-892
  
• Kallirroi Georgila, James Henderson, Oliver Lemon:
  Learning user simulations for information state update dialogue systems. 893-896
  
• Darío Martín-Iglesias, Yago Pereiro-Estevan, Ana I. García-Moral, Ascensión Gallardo-Antolín, Fernando Díaz-de-María:
  Design of a voice-enabled interface for real-time access to stock exchange from a PDA through GPRS. 897-900
  
• William Schuler, Tim Miller:
  Integrating denotational meaning into a DBN language model. 901-904
  
• Louis ten Bosch:
  Improving out-of-coverage language modelling in a multimodal dialogue system using small training sets. 905-908
  
• Olivier Galibert, Gabriel Illouz, Sophie Rosset:
  Ritel: an open-domain, human-computer dialog system. 909-912
  

Robust Speech Recognition I-IV

• Reinhold Haeb-Umbach, Joerg Schmalenstroeer:
  A comparison of particle filtering variants for speech feature enhancement. 913-916
  
• Ilyas Potamitis, Nikolaos D. Fakotakis:
  Enhancement of mel log-power spectrum of speech using particle filtering. 917-920
  
• Makoto Shozakai, Goshu Nagino:
  Improving robustness of speech recognition performance to aggregate of noises by two-dimensional visualization. 921-924
  
• Woohyung Lim, Bong Kyoung Kim, Nam Soo Kim:
  Feature compensation based on switching linear dynamic model and soft decision. 925-928
  
• Shilei Huang, Xiang Xie, Jingming Kuang:
  Using output probability distribution for improving speech recognition in adverse environment. 929-932
  
• Eric H. C. Choi:
  A generalized framework for compensation of mel-filterbank outputs in feature extraction for robust ASR. 933-936
  
• Hesham Tolba, Zili Li, Douglas D. O'Shaughnessy:
  Robust automatic speech recognition using a perceptually-based optimal spectral amplitude estimator speech enhancement algorithm in various low-SNR environments. 937-940
  
• Stephen So, Kuldip K. Paliwal:
  Improved noise-robustness in distributed speech recognition via perceptually-weighted vector quantisation of filterbank energies. 941-944
  
• Babak Nasersharif, Ahmad Akbari:
  Sub-band weighted projection measure for robust sub-band speech recognition. 945-948
  
• Jianping Deng, Martin Bouchard, Tet Hin Yeap:
  Noise compensation using interacting multiple kalman filters. 949-952
  
• Veronique Stouten, Hugo Van Hamme, Patrick Wambacq:
  Kalman and unscented kalman filter feature enhancement for noise robust ASR. 953-956
  
• Chia-Yu Wan, Lin-Shan Lee:
  Histogram-based quantization (HQ) for robust and scalable distributed speech recognition. 957-960
  
• Yong-Joo Chung:
  A data-driven approach for the model parameter compensation in noisy speech recognition. 961-964
  
• Satoshi Kobashikawa, Satoshi Takahashi, Yoshikazu Yamaguchi, Atsunori Ogawa:
  Rapid response and robust speech recognition by preliminary model adaptation for additive and convolutional noise. 965-968
  
• Saurabh Prasad, Stephen A. Zahorian:
  Nonlinear and linear transformations of speech features to compensate for channel and noise effects. 969-972
  
• Motoyuki Suzuki, Yusuke Kato, Akinori Ito, Shozo Makino:
  Construction method of acoustic models dealing with various background noises based on combination of HMMs. 973-976
  
• Haitian Xu, Zheng-Hua Tan, Paul Dalsgaard, Børge Lindberg:
  Robust speech recognition based on noise and SNR classification - a multiple-model framework. 977-980
  
• Hwa Jeon Song, Hyung Soon Kim:
  Eigen-environment based noise compensation method for robust speech recognition. 981-984
  
• Martin Graciarena, Horacio Franco, Gregory K. Myers, Victor Abrash:
  Robust feature compensation in nonstationary and multiple noise environments. 985-988
  
• Jasha Droppo, Alex Acero:
  Maximum mutual information SPLICE transform for seen and unseen conditions. 989-992
  
• Sven E. Krüger, Martin Schafföner, Marcel Katz, Edin Andelic, Andreas Wendemuth:
  Speech recognition with support vector machines in a hybrid system. 993-996
  
• Vincent Barreaud, Douglas D. O'Shaughnessy, Jean-Guy Dahan:
  Experiments on speaker profile portability. 997-1000
  
• Daniele Colibro, Luciano Fissore, Claudio Vair, Emanuele Dalmasso, Pietro Laface:
  A confidence measure invariant to language and grammar. 1001-1004
  
• Ken Schutte, James R. Glass:
  Robust detection of sonorant landmarks. 1005-1008
  

Speech Production I

• Amélie Rochet-Capellan, Jean-Luc Schwartz:
  The labial-coronal effect and CVCV stability during reiterant speech production: an acoustic analysis. 1009-1012
  
• Amélie Rochet-Capellan, Jean-Luc Schwartz:
  The labial-coronal effect and CVCV stability during reiterant speech production: an articulatory analysis. 1013-1016
  
• Mitsuhiro Nakamura:
  Articulatory constraints and coronal stops: an EPG study. 1017-1020
  
• Vincent Robert, Brigitte Wrobel-Dautcourt, Yves Laprie, Anne Bonneau:
  Strategies of labial coarticulation. 1021-1024
  
• Jianwu Dang, Jianguo Wei, Takeharu Suzuki, Pascal Perrier:
  Investigation and modeling of coarticulation during speech. 1025-1028
  
• Fang Hu:
  Tongue kinematics in diphthong production in Ningbo Chinese. 1029-1032
  
• Takayuki Arai:
  Comparing tongue positions of vowels in oral and nasal contexts. 1033-1036
  
• Slim Ouni:
  Can we retrieve vocal tract dynamics that produced speech? toward a speaker articulatory strategy model. 1037-1040
  
• Pascal Perrier, Liang Ma, Yohan Payan:
  Modeling the production of VCV sequences via the inversion of a biomechanical model of the tongue. 1041-1044
  
• Xiaochuan Niu, Alexander Kain, Jan P. H. van Santen:
  Estimation of the acoustic properties of the nasal tract during the production of nasalized vowels. 1045-1048
  
• Kohichi Ogata:
  A web-based articulatory speech synthesis system for distance education. 1049-1052
  
• Paavo Alku, Matti Airas, Tomas Bäckström, Hannu Pulakka:
  Group delay function as a means to assess quality of glottal inverse filtering. 1053-1056
  
• Eva Björkner, Johan Sundberg, Paavo Alku:
  Subglottal pressure and NAQ variation in voice production of classically trained baritone singers. 1057-1060
  
• Gunnar Fant, Anita Kruckenberg:
  Covariation of subglottal pressure, F0 and intensity. 1061-1064
  
• Javier Pérez, Antonio Bonafonte:
  Automatic voice-source parameterization of natural speech. 1065-1068
  
• Chakir Zeroual, John H. Esling, Lise Crevier-Buchman:
  Physiological study of whispered speech in Moroccan Arabic. 1069-1072
  
• C. P. Moura, D. Andrade, L. M. Cunha, M. J. Cunha, H. Vilarinho, H. Barros, Diamantino Freitas, M. Pais-Clemente:
  Voice quality in down syndrome children treated with rapid maxillary expansion. 1073-1076
  
• Julien Hanquinet, Francis Grenez, Jean Schoentgen:
  Synthesis of disordered speech. 1077-1080
  
• Julie Fontecave, Frédéric Berthommier:
  Quasi-automatic extraction of tongue movement from a large existing speech cineradiographic database. 1081-1084
  
• Shimon Sapir, Ravit Cohen Mimran:
  The working memory token test (WMTT): preliminary findings in young adults with and without dyslexia. 1085-1088
  
• Sérgio Paulo, Luís C. Oliveira:
  Reducing the corpus-based TTS signal degradation due to speaker's word pronunciations. 1089-1092
  
• Wai-Sum Lee:
  A phonetic study of the "er-hua" rimes in Beijing Mandarin. 1093-1096
  

Acoustic Processing for ASR I-III

• Li Deng, Dong Yu, Alex Acero:
  Learning statistically characterized resonance targets in a hidden trajectory model of speech coarticulation and reduction. 1097-1100
  
• Daniil Kocharov, András Zolnay, Ralf Schlüter, Hermann Ney:
  Articulatory motivated acoustic features for speech recognition. 1101-1104
  
• Shinji Watanabe, Atsushi Nakamura:
  Effects of Bayesian predictive classification using variational Bayesian posteriors for sparse training data in speech recognition. 1105-1108
  
• Yu Tsao, Jinyu Li, Chin-Hui Lee:
  A study on separation between acoustic models and its applications. 1109-1112
  
• Mohamed Afify:
  Extended baum-welch reestimation of Gaussian mixture models based on reverse Jensen inequality. 1113-1116
  
• Asela Gunawardana, Milind Mahajan, Alex Acero, John C. Platt:
  Hidden conditional random fields for phone classification. 1117-1120
  

Signal Analysis, Processing and Feature Estimation I-III

• Francesco Gianfelici, Giorgio Biagetti, Paolo Crippa, Claudio Turchetti:
  Asymptotically exact AM-FM decomposition based on iterated hilbert transform. 1121-1124
  
• Athanassios Katsamanis, Petros Maragos:
  Advances in statistical estimation and tracking of AM-FM speech components. 1125-1128
  
• Jonathan Darch, Ben P. Milner, Saeed Vaseghi:
  Formant frequency prediction from MFCC vectors in noisy environments. 1129-1132
  
• S. R. Mahadeva Prasanna, B. Yegnanarayana:
  Detection of vowel onset point events using excitation information. 1133-1136
  
• João P. Cabral, Luís C. Oliveira:
  Pitch-synchronous time-scaling for prosodic and voice quality transformations. 1137-1140
  
• Yasunori Ohishi, Masataka Goto, Katunobu Itou, Kazuya Takeda:
  Discrimination between singing and speaking voices. 1141-1144
  

Spoken Language Resources and Technology Evaluation I, II

• Douglas Jones, Wade Shen, Elizabeth Shriberg, Andreas Stolcke, Teresa M. Kamm, Douglas A. Reynolds:
  Two experiments comparing reading with listening for human processing of conversational telephone speech. 1145-1148
  
• Sylvain Galliano, Edouard Geoffrois, Djamel Mostefa, Khalid Choukri, Jean-François Bonastre, Guillaume Gravier:
  The ESTER phase II evaluation campaign for the rich transcription of French broadcast news. 1149-1152
  
• Takashi Saito:
  A method of multi-layered speech segmentation tailored for speech synthesis. 1153-1156
  
• Sérgio Paulo, Luís C. Oliveira:
  Generation of word alternative pronunciations using weighted finite state transducers. 1157-1160
  
• Helmer Strik, Diana Binnenpoorte, Catia Cucchiarini:
  Multiword expressions in spontaneous speech: do we really speak like that? 1161-1164
  
• Jáchym Kolár, Jan Svec, Stephanie Strassel, Christopher Walker, Dagmar Kozlíková, Josef Psutka:
  Czech spontaneous speech corpus with structural metadata. 1165-1168
  

Early Language Acquisition

• Kentaro Ishizuka, Ryoko Mugitani, Hiroko Kato Solvang, Shigeaki Amano:
  A longitudinal analysis of the spectral peaks of vowels for a Japanese infant. 1169-1172
  
• Krisztina Zajdó, Jeannette M. van der Stelt, Ton G. Wempe, Louis C. W. Pols:
  Cross-linguistic comparison of two-year-old children's acoustic vowel spaces: contrasting Hungarian with dutch. 1173-1176
  
• Britta Lintfert, Katrin Schneider:
  Acoustic correlates of contrastive stress in German children. 1177-1180
  
• Giampiero Salvi:
  Ecological language acquisition via incremental model-based clustering. 1181-1184
  
• Tamami Sudo, Ken Mogi:
  Perceptual and linguistic category formation in infants. 1185-1188
  

Multi-modal / Multi-media Processing I, II

• Raghunandan S. Kumaran, Karthik Narayanan, John N. Gowdy:
  Myoelectric signals for multimodal speech recognition. 1189-1192
  
• Philippe Daubias:
  Is color information really useful for lip-reading ? (or what is lost when color is not used). 1193-1196
  
• Islam Shdaifat, Rolf-Rainer Grigat:
  A system for audio-visual speech recognition. 1197-1200
  
• Norihide Kitaoka, Hironori Oshikawa, Seiichi Nakagawa:
  Multimodal interface for organization name input based on combination of isolated word recognition and continuous base-word recognition. 1201-1204
  
• Yosuke Matsusaka:
  Recognition of (3) party conversation using prosody and gaze. 1205-1208
  
• Dongdong Li, Yingchun Yang, Zhaohui Wu:
  Combining voiceprint and face biometrics for speaker identification using SDWS. 1209-1212
  
• Neil Cooke, Martin Russell:
  Using the focus of visual attention to improve spontaneous speech recognition. 1213-1216
  
• Sabri Gurbuz:
  Real-time outer lip contour tracking for HCI applications. 1217-1220
  
• Jing Huang, Karthik Visweswariah:
  Improving lip-reading with feature space transforms for multi-stream audio-visual speech recognition. 1221-1224
  
• Hansjörg Mixdorff, Denis Burnham, Guillaume Vignali, Patavee Charnvivit:
  Are there facial correlates of Thai syllabic tones? 1225-1228
  
• Rowan Seymour, Ji Ming, Darryl Stewart:
  A new posterior based audio-visual integration method for robust speech recognition. 1229-1232
  

Bridging the Gap ASR-HSR

• Sorin Dusan, Lawrence R. Rabiner:
  On integrating insights from human speech perception into automatic speech recognition. 1233-1236
  
• Odette Scharenborg:
  Parallels between HSR and ASR: how ASR can contribute to HSR. 1237-1240
  
• Louis ten Bosch, Odette Scharenborg:
  ASR decoding in a computational model of human word recognition. 1241-1244
  
• Viktoria Maier, Roger K. Moore:
  An investigation into a simulation of episodic memory for automatic speech recognition. 1245-1248
  
• Eric Fosler-Lussier, C. Anton Rytting, Soundararajan Srinivasan:
  Phonetic ignorance is bliss: investigating the effects of phonetic information reduction on ASR performance. 1249-1252
  
• Marcus Holmberg, David Gelbart, Ulrich Ramacher, Werner Hemmert:
  Automatic speech recognition with neural spike trains. 1253-1256
  
• Michael J. Carey, Tuan P. Quang:
  A speech similarity distance weighting for robust recognition. 1257-1260
  
• Takao Murakami, Kazutaka Maruyama, Nobuaki Minematsu, Keikichi Hirose:
  Japanese vowel recognition based on structural representation of speech. 1261-1264
  
• Soundararajan Srinivasan, DeLiang Wang:
  Modeling the perception of multitalker speech. 1265-1268
  
• Sue Harding, Jon P. Barker, Guy J. Brown:
  Binaural feature selection for missing data speech recognition. 1269-1272
  
• Thorsten Wesker, Bernd T. Meyer, Kirsten Wagener, Jörn Anemüller, Alfred Mertins, Birger Kollmeier:
  Oldenburg logatome speech corpus (OLLO) for speech recognition experiments with humans and machines. 1273-1276
  

Speech Recognition - Language Modelling I-III

• Jen-Wei Kuo, Berlin Chen:
  Minimum word error based discriminative training of language models. 1277-1280
  
• A. Ghaoui, François Yvon, Chafic Mokbel, Gérard Chollet:
  On the use of morphological constraints in n-gram statistical language model. 1281-1284
  
• Elvira I. Sicilia-Garcia, Ji Ming, F. Jack Smith:
  A posteriori multiple word-domain language model. 1285-1288
  
• Javier Dieguez-Tirado, Carmen García-Mateo, Antonio Cardenal López:
  Effective topic-tree based language model adaptation. 1289-1292
  
• Abhinav Sethy, Panayiotis G. Georgiou, Shrikanth Narayanan:
  Building topic specific language models from webdata using competitive models. 1293-1296
  
• Carlos Troncoso, Tatsuya Kawahara:
  Trigger-based language model adaptation for automatic meeting transcription. 1297-1300
  
• Jacques Duchateau, Dong Hoon Van Uytsel, Hugo Van Hamme, Patrick Wambacq:
  Statistical language models for large vocabulary spontaneous speech recognition in dutch. 1301-1304
  
• Alexandre Allauzen, Jean-Luc Gauvain:
  Diachronic vocabulary adaptation for broadcast news transcription. 1305-1308
  
• Vesa Siivola, Bryan L. Pellom:
  Growing an n-gram language model. 1309-1312
  
• Harald Hning, Manuel Kirschner, Fritz Class, André Berton, Udo Haiber:
  Embedding grammars into statistical language models. 1313-1316
  
• Simo Broman, Mikko Kurimo:
  Methods for combining language models in speech recognition. 1317-1320
  
• Airenas Vaiciunas, Gailius Raskinis:
  Review of statistical modeling of highly inflected lithuanian using very large vocabulary. 1321-1324
  
• Genevieve Gorrell, Brandyn Webb:
  Generalized hebbian algorithm for incremental latent semantic analysis. 1325-1328
  
• Arnar Thor Jensson, Edward W. D. Whittaker, Koji Iwano, Sadaoki Furui:
  Language model adaptation for resource deficient languages using translated data. 1329-1332
  
• Petra Witschel, Sergey Astrov, Gabriele Bakenecker, Josef G. Bauer, Harald Höge:
  POS-based language models for large vocabulary speech recognition on embedded systems. 1333-1336
  

Speech Recognition - Pronunciation Modelling

• Je Hun Jeon, Minhwa Chung:
  Automatic generation of domain-dependent pronunciation lexicon with data-driven rules and rule adaptation. 1337-1340
  
• Michael Tjalve, Mark Huckvale:
  Pronunciation variation modelling using accent features. 1341-1344
  
• Khiet P. Truong, Ambra Neri, Febe de Wet, Catia Cucchiarini, Helmer Strik:
  Automatic detection of frequent pronunciation errors made by L2-learners. 1345-1348
  
• Josef Psutka, Pavel Ircing, Josef V. Psutka, Jan Hajic, William J. Byrne, Jirí Mírovský:
  Automatic transcription of Czech, Russian, and Slovak spontaneous speech in the MALACH project. 1349-1352
  
• Stéphane Dupont, Christophe Ris, Laurent Couvreur, Jean-Marc Boite:
  A study of implicit and explicit modeling of coarticulation and pronunciation variation. 1353-1356
  
• Shinya Takahashi, Tsuyoshi Morimoto, Sakashi Maeda, Naoyuki Tsuruta:
  Detection of coughs from user utterances using imitated phoneme model. 1357-1360
  
• V. Ramasubramanian, P. Srinivas, T. V. Sreenivas:
  Stochastic pronunciation modeling by ergodic-HMM of acoustic sub-word units. 1361-1364
  
• Chen Liu, Lynette Melnar:
  An automated linguistic knowledge-based cross-language transfer method for building acoustic models for a language without native training data. 1365-1368
  
• Ghazi Bouselmi, Dominique Fohr, Irina Illina, Jean Paul Haton:
  Fully automated non-native speech recognition using confusion-based acoustic model integration. 1369-1372
  

Prosodic Structure

• Véronique Aubergé, Albert Rilliard:
  The focus prosody: more than a simple binary function. 1373-1376
  
• Martha Dalton, Ailbhe Ní Chasaide:
  Peak timing in two dialects of connaught irish. 1377-1380
  
• Janet Fletcher:
  Compound rises and "uptalk" in spoken English. 1381-1384
  
• Li-chiung Yang:
  Duration and the temporal structure of Mandarin discourse. 1385-1388
  
• Bei Wang:
  Prosodic realization of split noun phrases in Mandarin Chinese compared in topic and focus contexts. 1389-1392
  
• Ziyu Xiong:
  Downstep effect on disyllabic words of citation forms in standard Chinese. 1393-1396
  
• Jinfu Ni, Hisashi Kawai, Keikichi Hirose:
  Estimation of intonation variation with constrained tone transformations. 1397-1400
  
• Ho-hsien Pan:
  Voice quality of falling tones in taiwan min. 1401-1404
  
• Chiu-yu Tseng, Bau-Ling Fu:
  Duration, intensity and pause predictions in relation to prosody organization. 1405-1408
  
• Jiahong Yuan, Jason M. Brenier, Daniel Jurafsky:
  Pitch accent prediction: effects of genre and speaker. 1409-1412
  
• Hiroya Fujisaki, Sumio Ohno:
  Analysis and modeling of fundamental frequency contours of hindi utterances. 1413-1416
  
• Natasha Govender, Etienne Barnard, Marelie H. Davel:
  Fundamental frequency and tone in isizulu: initial experiments. 1417-1420
  
• Judith Bishop, Marc Peake, Dmitry Sityaev:
  Intonational sequences in tuscan Italian. 1421-1424
  
• Caterina Petrone:
  Effects of raddoppiamento sintattico on tonal alignment in Italian. 1425-1428
  
• Tomás Dubeda, Jan Votrubec:
  Acoustic analysis of Czech stress: intonation, duration and intensity revisited. 1429-1432
  
• Mohamed Yeou:
  Variability of F0 peak alignment in moroccan Arabic accentual focus. 1433-1436
  
• Anne Lacheret, Ch. Lyche, Michel Morel:
  Phonological analysis of schwa and liaison within the PFC project (phonologie du fran ais contemporain): how determinant are the prosodic factors? 1437-1440
  
• Plínio A. Barbosa, Pablo Arantes, Alexsandro R. Meireles, Jussara M. Vieira:
  Abstractness in speech-metronome synchronisation: P-centres as cyclic attractors. 1441-1444
  

Applications of Confidence Related Measures to ASR

• Makoto Yamada, Tsuneo Kato, Masaki Naito, Hisashi Kawai:
  Improvement of rejection performance of keyword spotting using anti-keywords derived from large vocabulary considering acoustical similarity to keywords. 1445-1448
  
• Ralf Schlüter, T. Scharrenbach, Volker Steinbiss, Hermann Ney:
  Bayes risk minimization using metric loss functions. 1449-1452
  
• Akio Kobayashi, Kazuo Onoe, Shoei Sato, Toru Imai:
  Word error rate minimization using an integrated confidence measure. 1453-1456
  
• Bin Dong, Qingwei Zhao, Yonghong Yan:
  Fast confidence measure algorithm for continuous speech recognition. 1457-1460
  
• Hamed Ketabdar, Jithendra Vepa, Samy Bengio, Hervé Bourlard:
  Developing and enhancing posterior based speech recognition systems. 1461-1464
  
• Peng Liu, Ye Tian, Jian-Lai Zhou, Frank K. Soong:
  Background model based posterior probability for measuring confidence. 1465-1468
  

Multilingual TTS

• Laura Mayfield Tomokiyo, Alan W. Black, Kevin A. Lenzo:
  Foreign accents in synthetic speech: development and evaluation. 1469-1472
  
• Raul Fernandez, Wei Zhang, Ellen Eide, Raimo Bakis, Wael Hamza, Yi Liu, Michael Picheny, John F. Pitrelli, Yong Qing, Zhiwei Shuang, Li Qin Shen:
  Toward multiple-language TTS: experiments in English and Mandarin. 1473-1476
  
• Javier Latorre, Koji Iwano, Sadaoki Furui:
  Cross-language synthesis with a polyglot synthesizer. 1477-1480
  
• Mucemi Gakuru, Frederick K. Iraki, Roger Tucker, Ksenia Shalonova, Kamanda Ngugi:
  Development of a Kiswahili text to speech system. 1481-1484
  
• Jaime Botella Ordinas, Volker Fischer, Claire Waast-Richard:
  Multilingual models in the IBM bilingual text-to-speech systems. 1485-1488
  
• Artur Janicki, Piotr Herman:
  Reconstruction of Polish diacritics in a text-to-speech system. 1489-1492
  

Speech Bandwidth Extension

• Hiroyuki Ehara, Toshiyuki Morii, Masahiro Oshikiri, Koji Yoshida, Kouichi Honma:
  Design of bandwidth scalable LSF quantization using interframe and intraframe prediction. 1493-1496
  
• Bernd Geiser, Peter Jax, Peter Vary:
  Artificial bandwidth extension of speech supported by watermark-transmitted side information. 1497-1500
  
• Rongqiang Hu, Venkatesh Krishnan, David V. Anderson:
  Speech bandwidth extension by improved codebook mapping towards increased phonetic classification. 1501-1504
  
• Dhananjay Bansal, Bhiksha Raj, Paris Smaragdis:
  Bandwidth expansion of narrowband speech using non-negative matrix factorization. 1505-1508
  
• Michael L. Seltzer, Alex Acero, Jasha Droppo:
  Robust bandwidth extension of noise-corrupted narrowband speech. 1509-1512
  
• João P. Cabral, Luís C. Oliveira:
  Pitch-synchronous time-scaling for high-frequency excitation regeneration. 1513-1516
  

Spoken Language Resources and Technology Evaluation I, II

• Felix Burkhardt, Astrid Paeschke, M. Rolfes, Walter F. Sendlmeier, Benjamin Weiss:
  A database of German emotional speech. 1517-1520
  
• Philippe Boula de Mareüil, Christophe d'Alessandro, Gérard Bailly, Frédéric Béchet, Marie-Neige Garcia, Michel Morel, Romain Prudon, Jean Véronis:
  Evaluating the pronunciation of proper names by four French grapheme-to-phoneme converters. 1521-1524
  
• Filip Jurcícek, Jirí Zahradil, Libor Jelínek:
  A human-human train timetable dialogue corpus. 1525-1528
  
• Gloria Branco, Luís Almeida, Rui Gomes, Nuno Beires:
  A Portuguese spoken and multi-modal dialog corpora. 1529-1532
  
• Joyce Y. C. Chan, P. C. Ching, Tan Lee:
  Development of a Cantonese-English code-mixing speech corpus. 1533-1536
  
• Andrej Zgank, Darinka Verdonik, Aleksandra Zögling Markus, Zdravko Kacic:
  BNSI Slovenian broadcast news database - speech and text corpus. 1537-1540
  
• Jan Volín, Radek Skarnitzl, Petr Pollák:
  Confronting HMM-based phone labelling with human evaluation of speech production. 1541-1544
  
• Stephanie Strassel, Jáchym Kolár, Zhiyi Song, Leila Barclay, Meghan Lammie Glenn:
  Structural metadata annotation: moving beyond English. 1545-1548
  
• Delphine Charlet, Sacha Krstulovic, Frédéric Bimbot, Olivier Boëffard, Dominique Fohr, Odile Mella, Filip Korkmazsky, Djamel Mostefa, Khalid Choukri, Arnaud Vallée:
  Neologos: an optimized database for the development of new speech processing algorithms. 1549-1552
  
• Cheng-Yuan Lin, Kuan-Ting Chen, Jyh-Shing Roger Jang:
  A hybrid approach to automatic segmentation and labeling for Mandarin Chinese speech corpus. 1553-1556
  
• Yuang-Chin Chiang, Min-Siong Liang, Hong-Yi Lin, Ren-Yuan Lyu:
  The multiple pronunciations in Taiwanese and the automatic transcription of Buddhist sutra with augmented read speech. 1557-1560
  
• Marelie H. Davel, Etienne Barnard:
  Bootstrapping pronunciation dictionaries: practical issues. 1561-1564
  
• Nigel G. Ward, Anais G. Rivera, Karen Ward, David G. Novick:
  Root causes of lost time and user stress in a simple dialog system. 1565-1568
  
• Julie A. Parisi, Douglas Brungart:
  Evaluating communication effectiveness in team collaboration. 1569-1572
  
• David Conejero, Alan Lounds, Carmen García-Mateo, Leandro Rodríguez Liñares, Raquel Mochales, Asunción Moreno:
  Bilingual aligned corpora for speech to speech translation for Spanish, English and Catalan. 1573-1576
  
• Hynek Boril, Petr Pollák:
  Design and collection of Czech Lombard speech database. 1577-1580
  
• Abe Kazemzadeh, Hong You, Markus Iseli, Barbara Jones, Xiaodong Cui, Margaret Heritage, Patti Price, Elaine Andersen, Shrikanth Narayanan, Abeer Alwan:
  TBALL data collection: the making of a young children's speech corpus. 1581-1584
  
• Hitomi Tohyama, Shigeki Matsubara, Nobuo Kawaguchi, Yasuyoshi Inagaki:
  Construction and utilization of bilingual speech corpus for simultaneous machine interpretation research. 1585-1588
  
• Rebecca A. Bates, Patrick Menning, Elizabeth Willingham, Chad Kuyper:
  Meeting acts: a labeling system for group interaction in meetings. 1589-1592
  
• Marius-Calin Silaghi, Rachna Vargiya:
  A new evaluation criteria for keyword spotting techniques and a new algorithm. 1593-1596
  
• Christoph Draxler, Alexander Steffen:
  Phattsessionz: recording 1000 adolescent speakers in schools in Germany. 1597-1600
  
• Solomon Teferra Abate, Wolfgang Menzel, Bairu Tafila:
  An Amharic speech corpus for large vocabulary continuous speech recognition. 1601-1604
  
• Hans Dolfing, David Reitter, Luís Almeida, Nuno Beires, Michael Cody, Rui Gomes, Kerry Robinson, Roman Zielinski:
  The FASil speech and multimodal corpora. 1605-1608
  
• Karin Müller:
  Revealing phonological similarities between German and dutch. 1609-1612
  

Large Vocabulary Speech Recognition Systems

• Dimitra Vergyri, Katrin Kirchhoff, Venkata Ramana Rao Gadde, Andreas Stolcke, Jing Zheng:
  Development of a conversational telephone speech recognizer for Levantine Arabic. 1613-1616
  
• Bhuvana Ramabhadran:
  Exploiting large quantities of spontaneous speech for unsupervised training of acoustic models. 1617-1620
  
• Che-Kuang Lin, Lin-Shan Lee:
  Improved spontaneous Mandarin speech recognition by disfluency interruption point (IP) detection using prosodic features. 1621-1624
  
• Jeff Z. Ma, Spyros Matsoukas:
  Improvements to the BBN RT04 Mandarin conversational telephone speech recognition system. 1625-1628
  
• Sakriani Sakti, Satoshi Nakamura, Konstantin Markov:
  Incorporating a Bayesian wide phonetic context model for acoustic rescoring. 1629-1632
  
• Abdelkhalek Messaoudi, Lori Lamel, Jean-Luc Gauvain:
  Modeling vowels for Arabic BN transcription. 1633-1636
  
• Mohamed Afify, Long Nguyen, Bing Xiang, Sherif Abdou, John Makhoul:
  Recent progress in Arabic broadcast news transcription at BBN. 1637-1640
  
• Spyros Matsoukas, Rohit Prasad, Srinivas Laxminarayan, Bing Xiang, Long Nguyen, Richard M. Schwartz:
  The 2004 BBN 1xRT recognition systems for English broadcast news and conversational telephone speech. 1641-1644
  
• Rohit Prasad, Spyros Matsoukas, Chia-Lin Kao, Jeff Z. Ma, D.-X. Xu, Thomas Colthurst, Owen Kimball, Richard M. Schwartz, Jean-Luc Gauvain, Lori Lamel, Holger Schwenk, Gilles Adda, Fabrice Lefèvre:
  The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system. 1645-1648
  
• Bing Xiang, Long Nguyen, Xuefeng Guo, Dongxin Xu:
  The BBN Mandarin broadcast news transcription system. 1649-1652
  
• Paul Deléglise, Yannick Estève, Sylvain Meignier, Téva Merlin:
  The LIUM speech transcription system: a CMU Sphinx III-based system for French broadcast news. 1653-1656
  
• Lori Lamel, Gilles Adda, Eric Bilinski, Jean-Luc Gauvain:
  Transcribing lectures and seminars. 1657-1660
  
• Thomas Hain, John Dines, Giulia Garau, Martin Karafiát, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
  Transcription of conference room meetings: an investigation. 1661-1664
  
• Jean-Luc Gauvain, Gilles Adda, Martine Adda-Decker, Alexandre Allauzen, Véronique Gendner, Lori Lamel, Holger Schwenk:
  Where are we in transcribing French broadcast news? 1665-1668
  
• Odette Scharenborg, Stephanie Seneff:
  Two-pass strategy for handling OOVs in a large vocabulary recognition task. 1669-1672
  
• Long Nguyen, Bing Xiang, Mohamed Afify, Sherif Abdou, Spyros Matsoukas, Richard M. Schwartz, John Makhoul:
  The BBN RT04 English broadcast news transcription system. 1673-1676
  
• Rong Zhang, Ziad Al Bawab, Arthur Chan, Ananlada Chotimongkol, David Huggins-Daines, Alexander I. Rudnicky:
  Investigations on ensemble based semi-supervised acoustic model training. 1677-1680
  
• Jan Nouza, Jindrich Zdánský, Petr David, Petr Cerva, Jan Kolorenc, Dana Nejedlová:
  Fully automated system for Czech spoken broadcast transcription with very large (300k+) lexicon. 1681-1684
  
• Mike Schuster, Takaaki Hori, Atsushi Nakamura:
  Experiments with probabilistic principal component analysis in LVCSR. 1685-1688
  
• Thang Tat Vu, Dung Tien Nguyen, Chi Mai Luong, John-Paul Hosom:
  Vietnamese large vocabulary continuous speech recognition. 1689-1692
  
• Takahiro Shinozaki, Mari Ostendorf, Les E. Atlas:
  Data sampling for improved speech recognizer training. 1693-1696