• 
  Paul Dalsgaard, Børge Lindberg, Henrik Benner, Zheng-Hua Tan (Eds.): EUROSPEECH 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd INTERSPEECH Event, Aalborg, Denmark, September 3-7, 2001. ISCA 2001

What do Industry and Universities Expect from Each Other? (Special Session)

• 
  Ilkka Niiniluoto: Universities and industry: marriage or co-operation between independent partners? 11-12
• 
  Yrjö Neuvo: Considerations on what industry expects from universities. 13-14
• 
  Gary W. Strong: A perspective on industry/university relationships in the US. 15-16
• 
  Khalid Choukri: ELRA contribution to bridge the gap between industry and academia. 17-18

Linguistic Modelling: Language Model Compression

• 
  Giulio Maltese, P. Bravetti, H. Crépy, B. J. Grainger, M. Herzog, Francisco Palou: Combining word- and class-based language models: a comparative study in several languages using automatic and manual word-clustering techniques. 21-24
• 
  Shuntaro Isogai, Katsuhiko Shirai, Hirofumi Yamamoto, Yoshinori Sagisaka: Multi-class composite n-gram language model using multiple word clusters and word successions. 25-28
• 
  Imed Zitouni, Kamel Smaïli, Jean Paul Haton: Statistical language model based on a hierarchical approach: MCnv. 29-32
• 
  Edward W. D. Whittaker, Bhiksha Raj: Quantization-based language model compression. 33-36

Speech Production: Voice Source

• 
  Gerrit Bloothooft, Mieke van Wijck, Peter Pabon: Relations between vocal registers in voice breaks. 39-42
• 
  Gordon Ramsay: A quasi-one-dimensional model of aerodynamic and acoustic flow in the time-varying vocal tract: source and excitation mechanisms. 43-46
• 
  Nathalie Henrich, Christophe d'Alessandro, Boris Doval: Spectral correlates of voice open quotient and glottal flow asymmetry : theory, limits and experimental data. 47-50
• 
  Federico Avanzini, Paavo Alku, Matti Karjalainen: One-delayed-mass model for efficient synthesis of glottal flow. 51-54

Speech Recognition and Understanding: Pronunciation and Subword Units

• 
  Thomas Fang Zheng, Zhanjiang Song, Pascale Fung, William Byrne: Modeling pronunciation variation using context-dependent weighting and b/s refined acoustic modeling. 57-60
• 
  Issam Bazzi, James R. Glass: Learning units for domain-independent out-of- vocabulary word modelling. 61-64
• 
  Hideharu Nakajima, Izumi Hirano, Yoshinori Sagisaka, Katsuhiko Shirai: Pronunciation variant analysis using speaking style parallel corpus. 65-68
• 
  Jan Kneissler, Dietrich Klakow: Speech recognition for huge vocabularies by using optimized sub-word units. 69-72
• 
  Kyung-Tak Lee, Christian Wellekens: Dynamic lexicon using phonetic features. 1413-1416
• 
  Ute Ziegenhain, Josef G. Bauer: Triphone tying techniques combining a-priori rules and data driven methods. 1417-1420
• 
  Louis ten Bosch, Nick Cremelie: Pronunciation modeling and lexical adaptation in midsize vocabulary ASR. 1421-1424
• 
  Yi Liu, Pascale Fung: Estimating pronunciation variations from acoustic likelihood score for HMM reconstruction. 1425-1428
• 
  Maximilian Bisani, Hermann Ney: Breadth-first search for finding the optimal phonetic transcription from multiple utterances. 1429-1432
• 
  Matthias Wolff, Matthias Eichner, Rüdiger Hoffmann: Improved data-driven generation of pronunciation dictionaries using an adapted word list. 1433-1436
• 
  Karen Livescu, James R. Glass: Segment-based recognition on the phonebook task: initial results and observations on duration modeling. 1437-1440
• 
  Søren Kamaric Riis, Morten With Pedersen, Kåre Jean Jensen: Multilingual text-to-phoneme mapping. 1441-1444
• 
  Ming-Yi Tsai, Fu-Chiang Chou, Lin-Shan Lee: Pronunciation variation analysis with respect to various linguistic levels and contextual conditions for Mandarin Chinese. 1445-1448
• 
  Laura Mayfield Tomokiyo: Hypothesis-driven accent discrimination. 1449-1452
• 
  Changxue Ma, Mark A. Randolph: An approach to automatic phonetic baseform generation based on Bayesian networks. 1453-1457
• 
  Hauke Schramm, Peter Beyerlein: Towards discriminative lexicon optimization. 1457-1460
• 
  Xiaodong He, Yunxin Zhao: Model complexity optimization for nonnative English speakers. 1461-1464
• 
  Tibor Fegyó, Péter Mihajlik, Péter Tatai, Géza Gordos: Pronunciation modeling in hungarian number recognition. 1465-1468

Phonetics and Phonology: Prosody and Others

• 
  Marc Swerts, Hanne Kloots, Steven Gillis, Georges De Schutter: Factors affecting schwa-insertion in final consonant clusters in standard dutch. 75-78
• 
  Leah Hitchcock, Steven Greenberg: Vowel height is intimately associated with stress accent in spontaneous american English discourse. 79-82
• 
  Dafydd Gibbon: Finite state prosodic analysis of african corpus resources. 83-86
• 
  Marc Schröder, Roddy Cowie, Ellen Douglas-Cowie, Machiel Westerdijk, Stan C. A. M. Gielen: Acoustic correlates of emotion dimensions in view of speech synthesis. 87-90
• 
  Hanny den Ouden, Jacques M. B. Terken: Measuring pitch range. 91-94
• 
  Dafydd Gibbon, Ulrike Gut: Measuring speech rhythm. 95-98
• 
  Mariapaola D'Imperio: Tonal alignment, scaling and slope in Italian question and statement tunes. 99-102
• 
  Antti Iivonen: Pragmatic temporal voice range profile as a tool in the research of speech styles. 103-106
• 
  Wooil Kim, Taeyun Kim, Sungjoo Ahn, Hanseok Ko: Model based stress decision method. 107-110
• 
  Torbjørn Nordgård, Arne Kjell Foldvik: Reduction of alternative pronunciations in the norwegian computational lexicon norkompleks. 111-114
• 
  Gorka Elordieta, José Ignacio Hualde: The role of duration as a correlate of accent in lekeitio basque. 115-118
• 
  Victoria Johansson, Merle Horne, Sven Strömqvist: Word final aspiration as a phrase boundary cue: data from spontaneous Swedish discourse. 119-122
• 
  Xipeng Shen, Bo Xu: Study and auto-detection of stress based on tonal pitch range in Mandarin. 123-126
• 
  Noam Amir, Ori Kerret, Dimitry Karlinski: Classifying emotions in speech: a comparison of methods. 127-130

Speech Perception: First and Second Language Learning

• 
  Dawn M. Behne, Peter E. Czigler, Kirk P. H. Sullivan: Development of vowel quantity perception in late childhood. 133-136
• 
  Byunggon Yang: A study on the production-perception link of English vowels produced by native and non-native speakers. 137-140
• 
  Takashi Otake, Yuka Yamaguchi: Japanese can be aware of syllables and morae: evidence from Japanese-English bilingual children. 141-144
• 
  Daniel E. Callan, Keiichi Tajima, Akiko E. Callan, Reiko Akahane-Yamada, Shinobu Masaki: Neural processes underlying perceptual learning of a difficult second language phonetic contrast. 145-148
• 
  Masahiko Komatsu, Kazuya Mori, Takayuki Arai, Yuji Murahara: Human language identification with reduced segmental information: comparison between monolinguals and bilinguals. 149-152

Speech Perception: Miscellaneous

• 
  Santiago Fernández, Sergio Feijóo: Coarticulatory effects in perception. 155-158
• 
  Sue Harding, Georg Meyer: A case for multi-resolution auditory scene analysis. 159-162
• 
  Lucie Ménard, Jean-Luc Schwartz, Louis-Jean Boë, Sonia Kandel, Nathalie Vallée: Perceptual identification and normalization of synthesized French vowels from birth to adulthood. 163-166
• 
  Lucie Ménard, Louis-Jean Boë: Perceptual categorization of maximal vowel spaces from birth to adulthood simulated by an articulatory model. 167-170
• 
  Maxine Eskenazi, Alan W. Black: A study on speech over the telephone and aging. 171-174
• 
  Marcia Chen, Abeer Alwan: On the perception of voicing for plosives in noise. 175-178
• 
  Jintao Jiang, Abeer Alwan, Edward T. Auer, Lynne E. Bernstein: Predicting visual consonant perception from physical measures. 179-182
• 
  William A. Ainsworth, T. Cervera: Effects of noise adaptation on the perception of voiced plosives in isolated syllables. 371-374
• 
  Makoto Hiroshige, Kenji Araki, Koji Tochinai: On differential limen of word-based local speechrate variation in Japanese expressed by duration ratio. 375-378
• 
  Wan Tokuma: A multidimensional scaling study of fricatives; a comparison of perceptual and physical dimensions. 379-382
• 
  Marc Swerts, Emiel Krahmer: Reconstructing dialogue history. 383-386
• 
  David House, Jonas Beskow, Björn Granström: Timing and interaction of visual cues for prominence in audiovisual speech perception. 387-390
• 
  Masahiko Komatsu, Shinichi Tokuma, Won Tokuma, Takayuki Arai: Modelling the perceptual identification of Japanese consonants from LPC cepstral distances. 391-394
• 
  Denis Burnham, Valter Ciocca, Stephanie Stokes: Auditory-visual perception of lexical tone. 395-398
• 
  Anders Eriksson, Gunilla C. Thunberg, Hartmut Traunmller: Syllable prominence: a matter of vocal effort, phonetic distinct-ness and top-down processing. 399-402
• 
  Hansjörg Mixdorff, Christina Widera: Perceived prominence in terms of a linguistically motivated quantitative intonation model. 403-406
• 
  Sarah Hawkins, Noël Nguyen: Perception of coda voicing from properties of the onset and nucleus of 'led' and 'let'. 407-410
• 
  L. Lin, Eliathamby Ambikairajah, W. H. Holmes: Auditory filter bank design using masking curves. 411-414
• 
  Dashtseren Erdenebat, Shigeyoshi Kitazawa, Tatsuya Kitamura: A new feature driven cochlear implant speech processing strategy. 415-418

Noise Robust Recognition: Frontend and Compensation Algorithms (Special Session)

• 
  Qifeng Zhu, Markus Iseli, Xiaodong Cui, Abeer Alwan: Noise robust feature extraction for ASR using the Aurora 2 database. 185-188
• 
  Daniel P. W. Ellis, Manuel J. Reyes Gomez: Investigations into tandem acoustic modeling for the Aurora task. 189-192
• 
  Bernt Andrassy, Damjan Vlaj, Christophe Beaugeant: Recognition performance of the siemens front-end with and without frame dropping on the Aurora 2 database. 193-196
• 
  Bojan Kotnik, Zdravko Kacic, Bogomir Horvat: A multiconditional robust front-end feature extraction with a noise reduction procedure based on improved spectral subtraction algorithm. 197-200
• 
  Johan de Veth, Laurent Mauuary, Bernhard Noé, Febe de Wet, Jürgen Sienel, Lou Boves, Denis Jouvet: Feature vector selection to improve ASR robustness in noisy conditions. 201-204
• 
  Dusan Macho, Climent Nadeu: Comparison of spectral derivative parameters for robust speech recognition. 205-208
• 
  Umit H. Yapanel, John H. L. Hansen, Ruhi Sarikaya, Bryan L. Pellom: Robust digit recognition in noise: an evaluation using the AURORA corpus. 209-212
• 
  Jon Barker, Martin Cooke, Phil D. Green: Robust ASR based on clean speech models: an evaluation of missing data techniques for connected digit recognition in noise. 213-217
• 
  Jasha Droppo, Li Deng, Alex Acero: Evaluation of the SPLICE algorithm on the Aurora2 database. 217-220
• 
  José C. Segura, Ángel de la Torre, M. Carmen Benítez, Antonio M. Peinado: Model-based compensation of the additive noise for continuous speech recognition. experiments using the Aurora II database and tasks. 221-224
• 
  Andrew C. Morris, Astrid Hagen, Hervé Bourlard: MAP combination of multi-stream HMM or HMM/ANN experts. 225-228
• 
  Bojan Jarc, Rudolf Babic: Second order statistics spectrum estimation method for robust speech recognition. 229-232
• 
  Kaisheng Yao, Jingdong Chen, Kuldip K. Paliwal, Satoshi Nakamura: Feature extraction and model-based noise compensation for noisy speech recognition evaluated on AURORA 2 task. 233-236

Linguistic Modelling: Language Model Adaptation

• 
  Marcello Federico, Nicola Bertoldi: Broadcast news LM adaptation using contemporary texts. 239-242
• 
  Mirjam Sepesy Maucec, Zdravko Kacic: Topic detection for language model adaptation of highly-inflected languages by using a fuzzy comparison function. 243-246
• 
  Kallirroi Georgila, Nikos Fakotakis, George K. Kokkinakis: Efficient stochastic finite-state networks for language modelling in spoken dialogue systems. 247-250
• 
  Karthik Visweswariah, Harry Printz: Language models conditioned on dialog state. 251-254
• 
  Langzhou Chen, Jean-Luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda-Decker: Using information retrieval methods for language model adaptation. 255-258

Speech Production: Articulation

• 
  Olov Engwall: Making the tongue model talk: merging MRI & EMA measurements. 261-264
• 
  Inger Moen, Hanne Gram Simonsen, Morten Huseby, John Grue: The relationship between intraoral air pressure and tongue/palate contact during the articulation of norwegian /t/ and /d/. 265-268
• 
  Ahmed M. Elgendy, Louis C. W. Pols: Mechanical versus perceptual constraints as determinants of articulatory strategy. 269-272
• 
  Bryan Gick, Ian Wilson: Pre-liquid excrescent schwa: what happens when vocalic targets conflict. 273-276
• 
  Slim Ouni, Yves Laprie: Exploring the null space of the acoustic-to- articulatory inversion using a hypercube codebook. 277-280

Speech Recognition and Understanding: Topic Detection and Information Retrieval

• 
  M. W. Theunissen, K. Scheffler, Johan A. du Preez: Phoneme-based topic spotting on the switchboard corpus. 283-286
• 
  Martin Franz, J. Scott McCarley, Todd Ward, Wei-Jing Zhu: Topic styles in IR and TDT: effect on system behavior. 287-290
• 
  Geoffrey Zweig, Jing Huang, Mukund Padmanabhan: Extracting caller information from voicemail. 291-294
• 
  Hong-Kwang Jeff Kuo, Chin-Hui Lee: A portability study on natural language call steering. 295-298
• 
  Berlin Chen, Hsin-Min Wang, Lin-Shan Lee: Improved spoken document retrieval by exploring extra acoustic and linguistic cues. 299-302

Phonetics and Phonology: Segmentals and Synthesis

• 
  Kimiko Tsukada: Native vs non-native production of English vowels in spontaneous speech: an acoustic phonetic study. 305-308
• 
  Silke Goronzy, Marina Sahakyan, Wolfgang Wokurek: Is non-native pronunciation modelling necessary ? 309-312
• 
  Yves Laprie, Anne Bonneau: Burst segmentation and evaluation of acoustic cues. 313-316
• 
  Theodor Granser, Sylvia Moosmller: The schwa in albanian. 317-320
• 
  Simone Ashby, Julie Carson-Berndsen, Gina Joue: A testbed for developing multilingual phonotactic descriptions. 321-324
• 
  Wing-Nga Fung, Sze-Lok Lau: A physiological analysis of nasals and nasalization in Chinese. 325-328
• 
  Robert E. Donovan: A component by component listening test analysis of the IBM trainable speech synthesis system. 329-332
• 
  Shimei Pan, Kathleen McKeown, Julia Hirschberg: Semantic abnormality and its realization in spoken language. 333-336
• 
  Nick Campbell: TALKING FOREIGN - concatenative speech synthesis and the language barrier. 337-340
• 
  Christian Jensen: Schwa-assimilation in danish synthetic speech. 341-344
• 
  Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi: Text-to-speech synthesis with arbitrary speaker's voice from average voice. 345-348
• 
  Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano: High quality voice conversion based on Gaussian mixture model with dynamic frequency warping. 349-352
• 
  Min Tang, Chao Wang, Stephanie Seneff: Voice transformations: from speech synthesis to mammalian vocalizations. 353-356
• 
  Juana M. Gutiérrez-Arriola, Juan Manuel Montero, José A. Vallejo, Ricardo de Córdoba, Rubén San Segundo, José Manuel Pardo: A new multi-speaker formant synthesizer that applies voice conversion techniques. 357-360
• 
  Mikiko Mashimo, Tomoki Toda, Kiyohiro Shikano, Nick Campbell: Evaluation of cross-language voice conversion based on GMM and straight. 361-364
• 
  Rachel Coulston: Ejective reduction in chaha is conditioned by more than prosodic position. 365-368

Noise Robust Recognition: Frontend (Special Session)

• 
  Hong Kook Kim, Richard C. Rose, Hong-Goo Kang: Acoustic feature compensation based on decomposition of speech and noise for ASR in noisy environments. 421-424
• 
  Yan Ming Cheng, Dusan Macho, Yuanjun Wei, Douglas Ealey, Holly Kelleher, David Pearce, William Kushner, Tenkasi Ramabadran: A robust front-end algorithm for distributed speech recognition. 425-428
• 
  M. Carmen Benítez, Lukas Burget, Barry Y. Chen, Stéphane Dupont, Harinath Garudadri, Hynek Hermansky, Pratibha Jain, Sachin S. Kajarekar, Nelson Morgan, Sunil Sivadas: Robust ASR front-end using spectral-based and discriminant features: experiments on the Aurora tasks. 429-432
• 
  Bernhard Noé, Jürgen Sienel, Denis Jouvet, Laurent Mauuary, Johan de Veth, Lou Boves, Febe de Wet: Noise reduction for noise robust feature extraction for distributed speech recognition. 433-436
• 
  Douglas Ealey, Holly Kelleher, David Pearce: Harmonic tunnelling: tracking non-stationary noises during speech. 437-440

Linguistic Modelling: Semantic Modelling

• 
  David Carter, Ian Gransden: Resource-limited sentence boundary detection. 443-446
• 
  Andrew N. Pargellis, Eric Fosler-Lussier, Alexandros Potamianos, Chin-Hui Lee: Metrics for measuring domain independence of semantic classes. 447-450
• 
  Xiaolong Mou, Stephanie Seneff, Victor Zue: Context-dependent probabilistic hierarchical sublexical modelling using finite state transducers. 451-454
• 
  Jerome R. Bellegarda, Kim E. A. Silverman: Data-driven semantic inference for unconstrained desktop command and control. 455-458
• 
  Martin Jansche: Information extraction via heuristics for a movie showtime query system. 459-462

Speech Perception: Recognition and Intelligibility

• 
  Takashi Otake, Anne Cutler: Recognition of (almost) spoken words: evidence from word play in Japanese. 465-468
• 
  Vincent Colotte, Yves Laprie, Anne Bonneau: Perceptual experiments on enhanced and slowed down speech sentences for second language acquisition. 469-473
• 
  Steven Greenberg, Takayuki Arai: The relation between speech intelligibility and the complex modulation spectrum. 473-476
• 
  Olivier Crouzet, William A. Ainsworth: Envelope information in speech processing: acoustic-phonetic analysis vs. auditory figure-ground segregation. 477-480
• 
  Patti Adank, Roeland Van Hout, Roel Smits: A comparison between human vowel normalization strategies and acoustic vowel transformation techniques. 481-484

Speech Recognition and Understanding: LVCSR

• 
  Pavel Ircing, Pavel Krbec, Jan Hajic, Josef Psutka, Sanjeev Khudanpur, Frederick Jelinek, William Byrne: On large vocabulary continuous speech recognition of highly inflectional language - czech. 487-490
• 
  Takahiro Shinozaki, Chiori Hori, Sadaoki Furui: Towards automatic transcription of spontaneous presentations. 491-494
• 
  Olivier Siohan, Akio Ando, Mohamed Afify, Hui Jiang, Chin-Hui Lee, Qi Li, Feng Liu, Kazuo Onoe, Frank K. Soong, Qiru Zhou: A real-time Japanese broadcast news closed-captioning system. 495-498
• 
  Peter Beyerlein, Xavier L. Aubert, Matthew Harris, Carsten Meyer, Hauke Schramm: Investigations on conversational speech recognition. 499-502
• 
  Yuqing Gao, Hakan Erdogan, Yongxin Li, Vaibhava Goel, Michael Picheny: Recent advances in speech recognition system for IBM DARPA communicator. 503-506
• 
  Daniel Willett, Erik McDermott, Yasuhiro Minami, Shigeru Katagiri: Time and memory efficient viterbi decoding for LVCSR using a precompiled search network. 847-850
• 
  Feng Liu, Mohamed Afify, Hui Jiang, Olivier Siohan: A new verification-based fast match approach to large vocabulary speech recognition. 851-854
• 
  Seiichi Nakagawa, Yukihisa Horibe: A fast calculation method in LVCSRS by time-skipping and clustering of probability density distributions. 855-858
• 
  Shinichi Homma, Akio Kobayashi, Shoei Sato, Toru Imai, Akio Ando: Speech recognition of Japanese news commentary. 859-862

Speech Synthesis: Systems and Prosody

• 
  Piero Cosi, Fabio Tesser, Roberto Gretter, Cinzia Avesani, Mike Macon: Festival speaks Italian! 509-512
• 
  Alex I. C. Monaghan, Mahmoud Kassaei, Mark Luckin, Mariscela Amador-Hernandez, Andrew Lowry, Daniel Faulkner, Fred Sannier: Multilingual TTS for computer telephony: the aculab approach. 513-516
• 
  Géza Kiss, Géza Németh, Gábor Olaszy, Géza Gordos: A flexible multilingual TTS development and speech research tool. 517-520
• 
  Esther Klabbers, Karlheinz Stöber, Raymond N. J. Veldhuis, Petra Wagner, Stefan Breuer: Speech synthesis development made easy: the bonn open synthesis system. 521-525
• 
  Gábor Olaszy, Géza Németh, Péter Olaszi: Automatic prosody generation - a model for hungarian. 525-528
• 
  Olga van Herwijnen, Jacques M. B. Terken: Evaluation of PROS-3 for the assignment of prosodic structure, compared to assignment by human experts. 529-532
• 
  Yoichi Yamashita, Tomoyoshi Ishida: Stochastic F0 contour model based on the clustering of F0 shapes of a syntactic unit. 533-536
• 
  Xuejing Sun, Ted H. Applebaum: Intonational phrase break prediction using decision tree and n-gram model. 537-540
• 
  A. Zaki, A. Rajouani, M. Najim: Synthesizing intonation of standard arabic language. 541-545
• 
  Dawei Xu, Hiroki Mori, Hideki Kasuya: Invariance of relative F0 change field of Chinese disyllabic words. 545-548
• 
  Achim F. Müller, Rüdiger Hoffmann: Accent label prediction by time delay neural networks using gating clusters. 549-553
• 
  Peter Juel Henrichsen: Transformation-based learning of danish stress assignment. 553-556
• 
  Stefan Baumann, Jürgen Trouvain: On the prosody of German telephone numbers. 557-560
• 
  Marc Schröder: Emotional speech synthesis: a review. 561-564
• 
  Kjell Gustafson, David House: Fun or boring? a web-based evaluation of expressive synthesis for children. 565-568

Speech Recognition and Understanding: Articulatory and Perceptual Approaches to ASR

• 
  Jingdong Chen, Kuldip K. Paliwal, Satoshi Nakamura: Sub-band based additive noise removal for robust speech recognition. 571-574
• 
  Yik-Cheung Tam, Brian Kan-Wing Mak: Development of an asynchronous multi-band system for continuous speech recognition. 575-578
• 
  Peter Jancovic, Ji Ming: A multi-band approach based on the probabilistic union model and frequency-filtering features for robust speech recognition. 579-582
• 
  Liang Gu, Kenneth Rose: Split-band perceptual harmonic cepstral coefficients as acoustic features for speech recognition. 583-586
• 
  Astrid Hagen, Hervé Bourlard: Error correcting posterior combination for robust multi-band speech recognition. 587-590
• 
  Bojana Gajic, Kuldip K. Paliwal: Robust parameters for speech recognition based on subband spectral centroid histograms. 591-594
• 
  William H. Edmondson, Li Zhang: Pseudo-articulatory representations and the recognition of syllable patterns in speech. 595-598
• 
  Joe Frankel, Simon King: ASR - articulatory speech recognition. 599-602
• 
  Jeff Z. Ma, Li Deng: Efficient decoding strategy for conversational speech recognition using state-space models for vocal-tract-resonance dynamics. 603-606
• 
  Katrin Weber, Samy Bengio, Hervé Bourlard: HMM2- extraction of formant structures and their use for robust ASR. 607-610
• 
  Xiaoqing Yu, Wanggen Wan, Daniel P. K. Lun: Auditory model based speech recognition in noisy environment. 611-614
• 
  Sascha Wendt, Gernot A. Fink, Franz Kummert: Forward masking for increased robustness in automatic speech recognition. 615-618
• 
  Qi Li, Frank K. Soong, Olivier Siohan: An auditory system-based feature for robust speech recognition. 619-622

Noise Robust Recognition: Robust Systems - What Helps? (Special Session)

• 
  Markus Lieb, Alexander Fischer: Experiments with the philips continuous ASR system on the AURORA noisy digits database. 625-628
• 
  George Saon, Juan M. Huerta, Ea-Ee Jan: Robust digit recognition in noisy environments: the IBM Aurora 2 system. 629-632
• 
  Mohamed Afify, Hui Jiang, Filipp Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran: Evaluating the Aurora connected digit recognition task - a bell labs approach. 633-636

Phonetics and Phonology: Segmentals

• 
  Cécile Fougeron, J. P. Goldman, Ulrich H. Frauenfelder: Liaison and schwa deletion in French: an effect of lexical frequency and competition? 639-642
• 
  Eric Zee, Wai-Sum Lee: An acoustical analysis of the vowels in beijing Mandarin. 643-646
• 
  Véronique Delvaux, Alain Soquet: Discriminant analysis of nasal vs. oral vowels in French: comparison between different parametric representations. 647-650
• 
  Didier Demolin, Véronique Delvaux: Whispery voiced nasal stops in rwanda. 651-654

Speech Production: Prosody

• 
  Gunnar Fant, Anita Kruckenberg, Johan Liljencrants, Antonis Botinis: Prominence correlates. a study of Swedish. 657-660
• 
  Sumio Ohno, Hiroya Fujisaki: Quantitative analysis of the effects of emphasis upon prosodic features of speech. 661-664
• 
  Grzegorz Dogil, Bernd Möbius: Towards a model of target oriented production of prosody. 665-668
• 
  Chilin Shih, Greg Kochanski: Prosody control for speaking and singing styles. 669-672
• 
  Greg Kochanski, Chilin Shih: Automated modeling of Chinese intonation in continuous speech. 911-914
• 
  Johan Frid: Prediction of intonation patterns of accented words in a corpus of read Swedish news through pitch contour stylization. 915-918
• 
  Paavo Alku, Juha Vintturi, Erkki Vilkman: The use of fundamental frequency raising as a strategy for increasing vocal intensity in soft, normal, and loud phonation. 919-922
• 
  Antonis Botinis, Marios Fourakis, Robert Bannert: Prosodic interactions on segmental durations ingreek. 923-926
• 
  Min Chu, Yongqiang Feng: Study on factors influencing durations of syllables in Mandarin. 927-930
• 
  Sofia Gustafson-Capková, Beáta Megyesi: A comparative study of pauses in dialogues and read speech. 931-934
• 
  Keiichi Takamaru, Makoto Hiroshige, Kenji Araki, Koji Tochinai: Detecting Japanese local speech rate deceleration in spontaneous conversational speech using a variable threshold. 935-938
• 
  Niels Reinholt Petersen: Modelling fundamental frequency in first post-tonic syllables in danish sentences. 939-942
• 
  Michelina Savino: Non-finality and pre-finality in bari Italian intonation: a preliminary account. 943-946
• 
  Hansjörg Mixdorff, Oliver Jokisch: Building an integrated prosodic model of German. 947-950
• 
  Omar A. G. Ibrahim, S. H. El-Ramly, Nemat S. Abdel Kader: A model of F0 contour for arabic affirmative and interrogative sentences. 951-954
• 
  Caroline L. Smith, Lisa A. Hogan: Variation in final lengthening as a function of topic structure. 955-958
• 
  Olga van Herwijnen, Jacques M. B. Terken: Do speakers realize the prosodic structure they say they do? 959-962
• 
  Marija Tabain, Guillaume Rolland, Christophe Savariaux: Coarticulatory effects at prosodic boundaries: some acoustic results. 963-966
• 
  Plínio A. Barbosa: Generating duration from a cognitively plausible model of rhythm production. 967-970

Speech Recognition and Understanding: Acoustic Modelling - I

• 
  Matthew N. Stuttle, M. J. F. Gales: A mixture of Gaussians front end for speech recognition. 675-678
• 
  Jing Zheng, John Butzberger, Horacio Franco, Andreas Stolcke: Improved maximum mutual information estimation training of continuous density HMMs. 679-682
• 
  Florent Perronnin, Roland Kuhn, Patrick Nguyen, Jean-Claude Junqua: Maximum-likelihood training of a bipartite acoustic model for speech recognition. 683-686
• 
  Ruhi Sarikaya, John H. L. Hansen: Analysis of the root-cepstrum for acoustic modeling and fast decoding in speech recognition. 687-690
• 
  Ellen Eide: Distinctive features for use in an automatic speech recognition system. 1613-1616
• 
  Jiyong Zhang, Thomas Fang Zheng, Jing Li, Chunhua Luo, Guoliang Zhang: Improved context-dependent acoustic modeling for continuous Chinese speech recognition. 1617-1620
• 
  Jacques Duchateau, Kris Demuynck, Dirk Van Compernolle, Patrick Wambacq: Class definition in discriminant feature analysis. 1621-1624
• 
  José C. Segura, M. Carmen Benítez, Ángel de la Torre, Antonio J. Rubio: Feature extraction from time-frequency matrices for robust speech recognition. 1625-1628
• 
  Peng Yu, Zuoying Wang: Using spatial correlation information in speech recognition. 1629-1632
• 
  Josef G. Bauer: On the choice of classes in MCE based discriminative HMM-training for speech recognizers used in the telephone environment. 1633-1636
• 
  Joseph Keshet, Dan Chazan, Ben-Zion Bobrovsky: Plosive spotting with margin classifiers. 1637-1640
• 
  Fabio Brugnara: Model agglomeration for context-dependent acoustic modeling. 1641-1644
• 
  Michael Levit, Allen L. Gorin, Jeremy H. Wright: Multipass algorithm for acquisition of salient acoustic morphemes. 1645-1648
• 
  Tadashi Emori, Koichi Shinoda: Rapid vocal tract length normalization using maximum likelihood estimation. 1649-1652
• 
  Kozo Okuda, Tomoko Matsui, Satoshi Nakamura: Towards the creation of acoustic models for stressed Japanese speech. 1653-1656
• 
  Akira Baba, Shinichi Yoshizawa, Miichi Yamada, Akinobu Lee, Kiyohiro Shikano: Elderly acoustic model for large vocabulary continuous speech recognition. 1657-1660
• 
  Jin-Song Zhang, Shuwu Zhang, Yoshinori Sagisaka, Satoshi Nakamura: A hybrid approach to enhance task portability of acoustic models in Chinese speech recognition. 1661-1664
• 
  Luis Javier Rodríguez, Inés Torres, Amparo Varona: Evaluation of sublexical and lexical models of acoustic disfluencies for spontaneous speech recognition in Spanish. 1665-1668
• 
  Murat Deviren, Khalid Daoudi: Structural learning of dynamic Bayesian networks in speech recognition. 1669-1672

Linguistic Modelling: Language Models

• 
  Shigehiko Onishi, Hirofumi Yamamoto, Yoshinori Sagisaka: Structured language model for class identification of out-of-vocabulary words arising from multiple wordclasses. 693-696
• 
  Takatoshi Jitsuhiro, Hirofumi Yamamoto, Setsuo Yamada, Yoshinori Sagisaka: New language models using phrase structures extracted from parse trees. 697-700
• 
  Elvira I. Sicilia-Garcia, Ji Ming, F. Jack Smith: Triggering individual word domains in n-gram language models. 701-704
• 
  Tomoyosi Akiba, Katunobu Itou: A structured statistical language model conditioned by arbitrarily abstracted grammatical categories based on GLR parsing. 705-708
• 
  Atsushi Matsui, Hiroyuki Segi, Akio Kobayashi, Toru Imai, Akio Ando: Speech recognition of broadcast sports news. 709-712
• 
  Shinsuke Mori, Masafumi Nishimura, Nobuyasu Itoh: Improvement of a structured language model: arbori-context tree. 713-716
• 
  Woosung Kim, Sanjeev Khudanpur, Jun Wu: Smoothing issues in the structured language model. 717-720
• 
  Xipeng Shen, Bo Xu: The study of the effect of training set on statistical language modeling. 721-724
• 
  Yannick Estève, Frédéric Béchet, Alexis Nasr, Renato de Mori: Stochastic finite state automata language model triggered by dialogue states. 725-728
• 
  Manny Rayner, John Dowding, Beth Ann Hockey: A baseline method for compiling typed unification grammars into context free language models. 729-732
• 
  Edward W. D. Whittaker, Bhiksha Raj: Comparison of width-wise and length-wise language model compression. 733-736
• 
  Vesa Siivola, Mikko Kurimo, Krista Lagus: Large vocabulary statistical language modeling for continuous speech recognition in finnish. 737-740
• 
  Ramón López-Cózar, Diego H. Milone: A new technique based on augmented language models to improve the performance of spoken dialogue systems. 741-744
• 
  Kazuyuki Takagi, Kazuhiko Ozeki: Pause information for dependency analysis of read Japanese sentences. 1041-1044
• 
  Berlin Chen, Hsin-Min Wang, Lin-Shan Lee: An HMM/n-gram-based linguistic processing approach for Mandarin spoken document retrieval. 1045-1048
• 
  Yi-Chung Lin, Huei-Ming Wang: Probabilistic concept verification for language understanding in spoken dialogue systems. 1049-1052
• 
  M. Oguzhan Külekci, Mehmed Özkan: Turkish word segmentation using morphological analyzer. 1053-1056
• 
  Pongthai Tarsaku, Virach Sornlertlamvanich, Rachod Thongprasirt: Thai grapheme-to-phoneme using probabilistic GLR parser. 1057-1060
• 
  Philippe Blache, Daniel Hirst: Aligning prosody and syntax in property grammars. 1061-1064
• 
  Melissa Barkat, Ioana Vasilescu: From perceptual designs to linguistic typology and automatic language identification : overview and perspectives. 1065-1068
• 
  Susan Fitt: Morphological approaches for an English pronunciation lexicon. 1069-1072
• 
  Gina Joue, Julie Carson-Berndsen: An embodiment paradigm for speech recognition systems. 1073-1076
• 
  Kui Xu, Fuliang Weng, Helen M. Meng, Po-Chui Luk: Multi-parser architecture for query processing. 1077-1080
• 
  Yi-Chia Chen, Yi-Chung Lin: Two-stage probabilistic approach to text segmentation. 1081-1084
• 
  Roeland Ordelman, Arjan van Hessen, Franciska de Jong: Lexicon optimization for dutch speech recognition in spoken document retrieval. 1085-1088
• 
  Tom Brøndsted: Evaluation of recent speech grammar standardization efforts. 1089-1092

Speaker Recognition: Identification, Verification and Tracking. Speech Recognition and Understanding: Language Identification

• 
  Douglas Brungart, Kimberly R. Scott, Brian D. Simpson: The influence of vocal effort on human speaker identification. 747-750
• 
  Robert Faltlhauser, Günther Ruske: Improving speaker recognition using phonetically structured Gaussian mixture models. 751-754
• 
  Conrad Sanderson, Kuldip K. Paliwal: Information fusion for robust speaker verification. 755-758
• 
  Takayuki Satoh, Takashi Masuko, Takao Kobayashi, Keiichi Tokuda: A robust speaker verification system against imposture using an HMM-based speech synthesis system. 759-762
• 
  Arun C. Surendran: Sequential decisions for faster and more flexible verification. 763-766
• 
  Wei-Ho Tsai, Y. C. Chu, Chao-Shih Huang, Wen-Whei Chang: Background learning of speaker voices for textindependent speaker identification. 767-771
• 
  Wei-Ho Tsai, Wen-Whei Chang, Chao-Shih Huang: Explicit exploitation of stochastic characteristics of test utterance for text-independent speaker identification. 771-774
• 
  Chai Wutiwiwatchai, Varin Achariyakulporn, Sawit Kasuriya: Improvement of speaker verification for Thai language. 775-778
• 
  Javier Rodríguez Saeta, Christian Koechling, Javier Hernando: Speaker identification for car infotainment applications. 779-782
• 
  Holger Schalk, Herbert Reininger, Stephan Euler: A system for text dependent speaker verification - field trial evaluation and simulation results. 783-786
• 
  Alvin F. Martin, Mark A. Przybocki: Speaker recognition in a multi-speaker environment. 787-790
• 
  Zhijian Ou, Zuoying Wang: A new DP-like speaker clustering algorithm. 791-794
• 
  P. Sivakumaran, J. Fortuna, Aladdin M. Ariyaeeinia: On the use of the Bayesian information criterion in multiple speaker detection. 795-798
• 
  Laurent Benarousse, Edouard Geoffrois: Preliminary experiments on language identification using broadcast news recordings. 799-802
• 
  Katrin Kirchhoff, Sonia Parandekar: Multi-stream statistical n-gram modeling with application to automatic language identification. 803-806

Phonetics and Phonology: Prominence and Timing

• 
  Barbertje M. Streefkerk, Louis C. W. Pols, Louis ten Bosch: Up to what level can acoustical and textual features predict prominence. 811-814
• 
  Hyunsong Chung, Mark Huckvale: Linguistic factors affecting timing in Korean with application to speech synthesis. 815-818
• 
  Felix Schaeffler: Measuring rhythmic deviation in second language speech. 819-822
• 
  Ian Maddieson: Good timing: place-dependent voice onset time in ejective stops. 823-826

Speech Synthesis: Concatenation

• 
  Hélène François, Olivier Boëffard: Design of an optimal continuous speech database for text-to-speech synthesis considered as a set covering problem. 829-832
• 
  Christos Vosnidis, Vassilios Digalakis: Use of clustering information for coarticulation compensation in speech synthesis by word concatenation. 833-836
• 
  Maria Founda, George Tambouratzis, Aimilios Chalamandaris, George Carayannis: Reducing spectral mismatches in concatenative speech synthesis via systematic database enrichment. 837-840
• 
  Attila Ferencz, Sung-Woo Choi, Ho-Eun Song, Myoung-Wan Koo: Hansori 2001 - corpus-based implementation of the Korean hansori text-to-speech synthesizer. 841-844
• 
  William J. Barry, Claus Nielsen, Ove Andersen: Must diphone synthesis be so unnatural? 975-978
• 
  Ann K. Syrdal: Phonetic effects on listener detection of vowel concatenation. 979-982
• 
  Olivier Boëffard: Variable-length acoustic units inference for text-to-speech synthesis. 983-986
• 
  Ivan Bulyko, Mari Ostendorf: Unit selection for speech synthesis using splicing costs with weighted finite state transducers. 987-990
• 
  Ka Man Law, Tan Lee, Wai H. Lau: Cantonese text-to-speech synthesis using sub-syllable units. 991-994

Speech Recognition and Understanding: Noise Robustness

• 
  Febe de Wet, Bert Cranen, Johan de Veth, Lou Boves: A comparison of LPC and FFT-based acoustic features for noise robust ASR. 865-868
• 
  Miichi Yamada, Akira Baba, Shinichi Yoshizawa, Yuichiro Mera, Akinobu Lee, Hiroshi Saruwatari, Kiyohiro Shikano: Unsupervised noisy environment adaptation algorithm using MLLR and speaker selection. 869-872
• 
  Zekeriya Tufekci, John N. Gowdy, Sabri Gurbuz, Eric K. Patterson: Applying parallel model compensation with mel-frequency discrete wavelet coefficients for noise-robust speech recognition. 873-876
• 
  Tai-Hwei Hwang, Kuo-Hwei Yuo, Hsiao-Chuan Wang: Linear interpolation of cepstral variance for noisy speech recognition. 877-880
• 
  Hiroshi Matsumoto, Akihiko Shimizu, Kazumasa Yamamoto: Evaluation of a generalized dynamic cepstrum in distant speech recognition. 881-884
• 
  Arnaud Martin, Géraldine Damnati, Laurent Mauuary: Robust speech/non-speech detection using LDA applied to MFCC for continuous speech recognition. 885-888
• 
  Edmondo Trentin, Marco Gori: Toward noise-tolerant acoustic models. 889-892
• 
  Nicholas W. D. Evans, John S. D. Mason: Noise estimation without explicit speech, non-speech detection: a comparison of mean, modal and median based approaches. 893-896
• 
  Rathi Chengalvarayan: Evaluation of front-end features and noise compensation methods for robust Mandarin speech recognition. 897-900
• 
  Brendan J. Frey, Li Deng, Alex Acero, Trausti T. Kristjansson: ALGONQUIN: iterating laplace's method to remove multiple types of acoustic distortion for robust speech recognition. 901-904
• 
  John H. L. Hansen, Ruhi Sarikaya, Umit H. Yapanel, Bryan L. Pellom: Robust speech recognition in noise: an evaluation using the SPINE corpus. 905-908
• 
  Man-Hung Siu, Yu-Chung Chan: Robust speech recognition against packet loss. 1095-1098
• 
  Masaki Naito, Shingo Kuroiwa, Tsuneo Kato, Tohru Shimizu, Norio Higuchi: Rapid CODEC adaptation for cellular phone speech recognition. 1099-1102
• 
  Ascensión Gallardo-Antolín, Carmen Peláez-Moreno, Fernando Díaz-de-María: A robust front-end for ASR over IP snd GSM networks: an integrated scenario. 1103-1106
• 
  Philippe Renevey, Rolf Vetter, Jens Krauss: Robust speech recognition using missing feature theory and vector quantization. 1107-1110
• 
  Ji Ming, Peter Jancovic, Philip Hanna, Darryl Stewart: Modeling the mixtures of known noise and unknown unexpected noise for robust speech recognition. 1111-1114
• 
  Takayoshi Kawamura, Kazuya Takeda, Fumitada Itakura: Robust speech recognition based on selective use of missing frequency band HMMs. 1115-1118
• 
  Ikuyo Masuda-Katsuse: A new method for speech recognition in the presence of non-stationary, unpredictable and high-level noise. 1119-1122
• 
  Bojan Kotnik, Zdravko Kacic, Bogomir Horvat: A computational efficient real time noise robust speech recognition based on improved spectral subtraction method. 1123-1126
• 
  Damjan Vlaj, Zdravko Kacic, Bogomir Horvat: The use of noisy frame elimination and frequency spectrum magnitude reduction in noise robust speech recognition. 1127-1130
• 
  Jen-Tzung Chien: Combined linear regression adaptation and Bayesian predictive classification for robust speech recognition. 1131-1134
• 
  Florian Hilger, Hermann Ney: Quantile based histogram equalization for noise robust speech recognition. 1135-1138
• 
  Kaisheng Yao, Kuldip K. Paliwal, Satoshi Nakamura: Sequential noise compensation by a sequential kullback proximal algorithm. 1139-1142

Signal Analysis: Microphone Arrays & Source Localisation

• 
  Athanasios Koutras, Evangelos Dermatas, George K. Kokkinakis: Blind speech separation of moving speakers using hybrid neural networks. 997-1000
• 
  Wolfgang Herbordt, Herbert Buchner, Walter Kellermann: Computationally efficient frequency-domain combination of acoustic echo cancellation and robust adaptive beamforming. 1001-1004
• 
  Michael L. Seltzer, Bhiksha Raj: Calibration of microphone arrays for improved speech recognition. 1005-1008
• 
  Athanasios Koutras, Evangelos Dermatas, George K. Kokkinakis: Improving simultaneous speech recognition in real room environments using overdetermined blind source separation. 1009-1012
• 
  Futoshi Asano, Masataka Goto, Katunobu Itou, Hideki Asoh: Real-time sound source localization and separation system and its application to automatic speech recognition. 1013-1016

Speech Recognition and Understanding: Audio-Visual Processing

• 
  Joohun Lee, Jin Young Kim: An efficient lipreading method using the symmetry of lip. 1019-1022
• 
  Martin Heckmann, Thorsten Wild, Frédéric Berthommier, Kristian Kroschel: Comparing audio- and a-posteriori-probability-based stream confidence measures for audio-visual speech recognition. 1023-1026
• 
  Gerasimos Potamianos, Chalapathy Neti, Giridharan Iyengar, Eric Helmuth: Large-vocabulary audio-visual speech recognition by machines and humans. 1027-1030
• 
  Philippe Daubias, Paul Deléglise: Evaluation of an automatically obtained shape and appearance model for automatic audio visual speech recognition. 1031-1034
• 
  Catherine Pelachaud, Emanuela Magno Caldognetto, Claudio Zmarich, Piero Cosi: An approach to an Italian talking head. 1035-1038

SIGshow (Special Session)

• 
  Jean-François Bonastre, Ivan Magrin-Chagnolleau, Stephan Euler, François Pellegrino, Régine André-Obrecht, John S. D. Mason, Frédéric Bimbot: SPeaker and language characterization (spLC): a special interest group (SIG) of ISCA. 1145-1148
• 
  Nick Campbell, Wolfgang Hess, Bernd Möbius, Jan P. H. van Santen: The ISCA special interest group on speech synthesis. 1149-1152
• 
  Dominic W. Massaro: Auditory visual speech processing. 1153-1156
• 
  Laila Dybkjær: SIGdial - special interest group on discourse and dialogue. 1345-1348
• 
  Philippe Delcloque: Integrating speech technology in language learning: an overview of the activities of inSTIL. 1349-1352
• 
  Climent Nadeu, Donncha Cróinín, Bojan Petek, Kepa Sarasola, Briony Williams: ISCA SALTMIL SIG: speech and language technology for minority languages. 1353-1556

Speech Synthesis: Prosody

• 
  Weijun Chen, Fuzong Lin, Jianmin Li, Bo Zhang: Training prosodic phrasing rules for Chinese TTS systems. 1159-1162
• 
  Per Olav Heggtveit, Jon Emil Natvig: Intonation modelling with a lexicon of natural F0 contours. 1163-1166
• 
  Kim E. A. Silverman, Jerome R. Bellegarda, Kevin A. Lenzo: Smooth contour estimation in data-driven pitch modelling. 1167-1170
• 
  Takashi Saito, Masaharu Sakamoto: Generating F0 contours by statistical manipulation of natural F0 shapes. 1171-1174
• 
  Julia Hirschberg, Owen Rambow: Learning prosodic features using a tree representation. 1175-1178

Applications: Multimodal Applications

• 
  Sabri Gurbuz, Eric K. Patterson, Zekeriya Tufekci, John N. Gowdy: Lip-reading from parametric lip contours for audio- visual speech recognition. 1181-1184
• 
  Simon Lucey, Sridha Sridharan, Vinod Chandran: An investigation of HMM classifier combination strategies for improved audio-visual speech recognition. 1185-1188
• 
  Niels Ole Bernsen, Laila Dybkjær: Combining multi-party speech and text exchanges over the internet. 1189-1192
• 
  Kazuhiro Nakadai, Ken-ichi Hidai, Hiroshi G. Okuno, Hiroaki Kitano: Real-time multiple speaker tracking by multi-modal integration for mobile robots. 1193-1196
• 
  Tsuneo Nitta, Kouichi Katsurada, Hirobumi Yamada, Yusaku Nakamura, Satoshi Kobayashi: XISL: an attempt to separate multimodal interactions from XML contents. 1197-1200

Speech Recognition and Understanding: Speaker Adaptation

• 
  Asela Gunawardana, William Byrne: Discriminative speaker adaptation with conditional maximum likelihood linear regression. 1203-1206
• 
  Patrick Kenny, Gilles Boulianne, Pierre Dumouchel: What is the best type of prior distribution for EMAP speaker adaptation? 1207-1210
• 
  Yoon Kim: Maximum-likelihood affine cepstral filtering (MLACF) technique for speaker normalization. 1211-1214
• 
  Bowen Zhou, John H. L. Hansen: A novel algorithm for rapid speaker adaptation based on structural maximum likelihood eigenspace mapping. 1215-1218
• 
  Shinichi Yoshizawa, Akira Baba, Kanako Matsunami, Yuichiro Mera, Miichi Yamada, Akinobu Lee, Kiyohiro Shikano: Evaluation on unsupervised speaker adaptation based on sufficient HMM statictics of selected speakers. 1219-1222

Speech Recognition and Understanding: Adaptation

• 
  Jia Lei, Xu Bo: A novel target-driven MLLR adaptation algorithm with multi-layer structure. 1225-1228
• 
  Frank Wallhoff, Daniel Willett, Gerhard Rigoll: Scaled likelihood linear regression for hidden Markov model adaptation. 1229-1232
• 
  Tor André Myrvoll, Kuldip K. Paliwal, Torbjørn Svendsen: Fast adaptation using constrained affine transformations with hierarchical priors. 1233-1236
• 
  Xiaoxing Liu, Baosheng Yuan, Yonghong Yan: A context adaptation approach for building context dependent models in LVCSR. 1237-1240
• 
  Fabrice Lefevre, Jean-Luc Gauvain, Lori Lamel: Improving genericity for task-independent speech recognition. 1241-1244
• 
  Driss Matrouf, Olivier Bellot, Pascal Nocera, Georges Linares, Jean-François Bonastre: A posteriori and a priori transformations for speaker adaptation in large vocabulary speech recognition systems. 1245-1248
• 
  Darryl W. Purnell, Elizabeth C. Botha: Bayesian methods for HMM speech recognition with limited training data. 1249-1252
• 
  Kwok-Man Wong, Brian Kan-Wing Mak: Rapid speaker adaptation using MLLR and subspace regression classes. 1253-1256