EUROSPEECH 1993: Berlin, Germany

Keynotes

• Janet M. Baker:
  Dictation, directories, and data bases; emerging PC applications forlarge vocabulary speech recognition.
  
• William J. Barry, Paul Dalsgaard:
  Speech database annotation. the importance of a multi-lingual approach.
  
• Lori Lamel, Jean-Luc Gauvain:
  Identifying non-linguistic speech features.
  
• Jeremy Peckham:
  A new generation of spoken dialogue systems: results and lessons from the sundial project.
  
• Roger K. Moore:
  Whither a theory of speech pattern processing?
  
• Peter Noll:
  Speech coding for communications.
  
• Hermann Ney:
  Modeling and search in continuous speech recognition.
  
• Maxine Eskenazi:
  Trends in speaking styles research.
  
• John S. Bridle:
  Models of speech recognition; personal perspectives on particular approaches.
  
• Kai-Fu Lee:
  The conversational computer: an apple perspective.
  
• Ute Jekosch:
  Speech quality assessment and evaluation.
  
• Jan P. H. van Santen:
  Timing in text-to-speech systems.
  
• Roberto Pieraccini, Esther Levin, Enrique Vidal:
  Learning how to understand language.
  

Speech Coding

• Kazunori Ozawa, Masahiro Serizawa, Toshiki Miyano, Toshiyuki Nomura:
  M-LCELP speech coding at bit-rates below 4kbps.
  
• Eduardo López Gonzalo, Luis A. Hernández-Gomez:
  Fast vector quantization using neural maps for CELP at 2400bps.
  
• Ulrich Balss, U. Kipper, Herbert Reininger, Dietrich Wolf:
  Improving the speech quality of CELP-coders by optimizing the long-term delay determination.
  
• Carmen García-Mateo, José Luis Alba-Castro, Luis A. Hernández Gómez:
  A stochastic speech coder with multi-band long-term prediction.
  
• B. W. M. Wery, Herman J. M. Steeneken:
  Intelligibility evaluation of 4-5 kbps CELP and MBE vocoders: the hermes program experiment.
  
• Przemyslaw Dymarski, Nicolas Moreau:
  Algorithms for the CELP coder with ternary excitation.
  
• M. Mauc, Geneviève Baudoin, M. Jelinek:
  Complexity reduction for federal standard 1016 CELP coder.
  
• Friedhelm Wuppermann, Christiane Antweiler, M. Kappelan:
  Objective analysis of the GSM half rate speech codec candidates.
  
• Ira A. Gerson, Mark A. Jasiuk:
  A 5600 BPS VSELP speech coder candidate for half-rate GSM.
  
• Ahmet M. Kondoz, Barry G. Evans, M. R. Suddle:
  A speech coder for TV programme description.
  
• Satoshi Miki, Kazunori Mano, Hitoshi Ohmuro, Takehiro Moriya:
  Pitch synchronous innovation CELP (PSI-CELP).
  
• Asunción Moreno, José A. R. Fonollosa, Josep Vidal:
  Vocoder design based on HOS.
  
• Nigel Sedgwick:
  Emulation of a formant vocoder at 600 and 800 bps.
  
• W. Ma, Ahmet M. Kondoz, Barry G. Evans:
  A pitch synchronized synthesizer for the IMBE vocoder.
  
• Thierry Dutoit, Henri Leich:
  An analysis of the performances of the MBE model when used in the context of a text-to-speech system.
  
• C. F. Chan:
  High-quality synthesis of LPC speech using multiband excitation model.
  
• Yair Shoham:
  High-quality speech coding at 2.4 kbps based on time-frequency interpolation.
  
• Luca Marcato, Enzo Mumolo:
  Coding of speech signal by fractal techniques.
  
• Naomi Asanuma, Hiromi Nagabuchi:
  A new reference signal for evaluating the quality of speech coded at low bit rates.
  
• Changxue Ma, Douglas D. O'Shaughnessy:
  A psychophysical study of fourier phase and amplitude coding of speech.
  

Articulatory Modelling

• Denis Beautemps, Pierre Badin, Rafael Laboissière:
  Recovery of vocal tract midsagittal and area functions from speech signal for vowels and fricative consonants.
  
• Shrikanth S. Narayanan, Abeer A. Alwan:
  Strange attractors and chaotic dynamics in the production of voiced and voiceless fricatives.
  
• Noël Nguyen, Philip Hoole:
  Frequency variations of the lowest main spectral peak in sibilant clusters.
  
• Hélène Loevenbruck, Pascal Perrier:
  Vocalic reduction : prediction of acoustic and articulatory variabilities with invariant motor commands.
  
• Christophe Savariaux, Pascal Perrier, Jean Pierre Orliaguet:
  Compensating for labial perturbation in a rounded vowel: an acoustic and articulatory study.
  
• Rudolph Sock, Anders Löfqvist:
  Resistance of bilabials /p, b/ to anticipatory labial and mandibular coarticulation from vowel types /i, a, u/.
  
• Mounir Jomaa, Christian Abry:
  Jaw phasings and velocity profiles in arabic.
  
• Morten Olesen:
  Derivation of the transfer function for a speech production model including the nasal cavity.
  
• Mats Båvegård, Jesper Högberg:
  Using artificial neural nets to compare different vocal tract models.
  
• Arne Kjell Foldvik, Ulf Kristiansen, Jorn Kvaerness:
  A time-evolving three-dimensional vocal tract model by means of magnetic resonance imaging (MRI).
  

Voice Source Analysis and Modelling

• Juergen Schroeter, Bert Cranen:
  Physiologically-motivated modeling of the voice source in articulatory analysis/synthesis.
  
• Luís C. Oliveira:
  Estimation of source parameters by frequency analysis.
  
• Helmer Strik, Bert Cranen, Lou Boves:
  Fitting a LF-model to inverse filter signals.
  
• Jean Schoentgen:
  Modelling the glottal pulse with a self-excited threshold auto-regressive model.
  
• Joachim Denzler, Ralf Kompe, Andreas Kießling, Heinrich Niemann, Elmar Nöth:
  Going back to the source: inverse filtering of the speech signal with ANNs.
  

HMM-Based Recognition System

• Manuel A. Leandro, José Manuel Pardo:
  Low cost speaker dependent isolated word speech preselection system using static phoneme pattern recognition.
  
• Lori Lamel, Jean-Luc Gauvain:
  High performance speaker-independent phone recognition using CDHMM.
  
• Jean-Luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda-Decker:
  Speaker-independent continuous speech dictation.
  
• Ernst Günter Schukat-Talamazzini, Heinrich Niemann, Wieland Eckert, Thomas Kuhn, S. Rieck:
  Automatic speech recognition without phonemes.
  
• Takashi Seino, Seiichi Nakagawa:
  Spoken language identification using ergodic HMM with emphasized state transition.
  

Speech Signal Processing

• Bruno Apolloni, Dario Crivelli, Marco Amato:
  Neural time warping.
  
• Philippe Le Cerf, Dirk Van Compernolle:
  Speaker independent small vocabulary speech recognition using MLPs for phonetic labeling.
  
• Andrzej Drygajlo:
  Multiresolution time-sequency speech processing based on orthogonal wavelet packet pulse forms.
  
• Eliathamby Ambikairajah, M. Keane, Liam Kilmartin, Graham Tattersall:
  The application of the wavelet transform for speech processing.
  
• Naoto Iwahashi, Yoshinori Sagisaka:
  Duration modelling with multiple split regression.
  
• Gerry Altmann, Duncan Young:
  Factors affecting adaptation to time-compressed speech.
  
• Marc Roelands, Werner Verhelst:
  Waveform similarity based overlap-add (WSOLA) for time-scale modification of speech: structures and evaluation.
  
• Hsiao-Chuan Wang, Hsiao-Fen Pai:
  A study on the weighting factors of two-dimensional cepstral distance measure.
  
• Yves Kamp, Changxue Ma:
  Connection between weighted LPC and higher-order statistics for AR model estimation.
  

Speaker Recognition

• Claude C. Chibelushi, John S. Mason, R. Deravi:
  Integration of acoustic and visual speech for speaker recognition.
  
• Claude Montacié, Jean-Luc Le Floch:
  Discriminant AR-vector models for free-text speaker verification.
  
• J. Thompson, John S. Mason:
  Within class optimization of cepstra for speaker recognition.
  
• Frédéric Bimbot, Luc Mathan:
  Text-free speaker recognition using an arithmetic-harmonic sphericity measure.
  

Data Bases, Speech Assessment, Noisy Speech

• Asunción Moreno, Dolors Poch, Antonio Bonafonte, Eduardo Lleida, Joaquim Llisterri, José B. Mariño, Climent Nadeu:
  Albayzin speech database: design of the phonetic corpus.
  
• Carlos M. Ribeiro, Isabel Trancoso, António Joaquim Serralheiro:
  A software tool for speech collection, recognition and reproduction.
  
• Matti Karjalainen, Toomas Altosaar:
  An object-oriented database for speech processing.
  
• Dominic S. F. Chan, Adrian Fourcin:
  Automatic annotation using multi-sensor data.
  
• Christoph Draxler, Hans G. Tillmann, Barbara Eisen:
  Prolog tools for accessing the phondat database of spoken German.
  
• Ute Jekosch:
  Cluster-similarity: a useful database for speech processing.
  
• Giuseppe Castagneri, Giuseppe Di Fabbrizio, A. Massone, Mario Oreglia:
  SIRVA - a large speech database collected on the Italian telephone network.
  
• Herman J. M. Steeneken, Jan A. Verhave, Tammo Houtgast:
  Objective assessment of speech communication systems; introduction of a software based procedure.
  
• Sven W. Danielsen:
  Enhanced direct assessment of speech input systems within the SAM-a esprit project.
  
• Pascale Nicolas, Pascal Romeas:
  Evaluation of prosody in the French version of multilingual text-to-speech synthesis: neutralising segmental information in preliminary tests.
  
• Sokol Saliu, Hideki Kasuya, Yasuo Endo, Yoshinobu Kikuchi:
  A clinical voice evaluation system.
  
• Alan Wrench, Mary S. Jackson, Mervyn A. Jack, David S. Soutar, A. Gerry Robertson, Janet MacKenzie, John Laver:
  A speech therapy workstation for the assessment of segmental quality: voiceless fricatives.
  
• Josep M. Salavedra, Enrique Masgrau, Asunción Moreno, Xavier Jove:
  A speech enhancement system using higher order ar estimation in real environments.
  
• Régine Le Bouquin, Gérard Faucon, A. Akbariazirani:
  Proposal of a composite measure for the evaluation of noise cancelling methods in speech processing.
  
• P. M. Crozier, Barry M. G. Cheetham, C. Holt, E. Munday:
  The use of linear prediction and spectral scaling for improving speech enhancement.
  
• Helge B. D. Sørensen, Uwe Hartmann:
  Robust speaker-independent speech recognition using non-linear spectral subtraction based IMELDA.
  

Phonetics

• Willem H. Vieregge, A. P. A. Broeders:
  Intra- and interspeaker variation of /r/ in dutch.
  
• Mechtild Tronnier, Masatake Dantsuji:
  An acoustic approach to fricatives in Japanese and German.
  
• Céu Viana, Isabel Trancoso, Carlos M. Ribeiro, Amalia Andrade, Ernesto d'Andrade:
  The relationship between spelled and spoken portuguese: implications for speech synthesis and recognition.
  
• Mark S. Schmidt, S. Fitt, C. Scott, Mervyn A. Jack:
  Phonetic transcription standards for european names (ONOMASTICA).
  
• Ove Andersen, Paul Dalsgaard, William J. Barry:
  Data-driven identification of poly- and mono-phonemes for four european languages.
  
• Sheri Hunnicutt, Helen M. Meng, Stephanie Seneff, Victor W. Zue:
  Reversible letter-to-sound sound-to-letter generation based on parsing word morphology.
  
• Jan Moore, Peter Roach:
  The role of context in the automatic recognition of stressed syllables.
  
• Duncan Young, Gerry Altmann, Anne Cutler, Dennis Norris:
  Metrical structure and the perception of time-compressed speech.
  
• Valerie Pasdeloup, José Morais, Régine Kolinsky:
  Are stress and phonemic string processed separately? evidence from speech illusions.
  

Phoneme Classification and Labelling

• R. J. J. H. van Son, Louis C. W. Pols:
  Vowel identification as influenced by vowel duration and formant track shape.
  
• William Goldenthal, James R. Glass:
  Modelling spectral dynamics for vowel classification.
  
• Milan Stamenkovic, Juraj Bakran, Peter Tancig, Marijan Miletic:
  Perceptive and spectral volumes of synthesized and natural vowels.
  
• Ryszard Gubrynowicz, Adam Wrzoskowicz:
  Labeller - a system for automatic labelling of speech continuous signal.
  
• Ake Andersson, Holger Broman:
  Towards automatic speech-to-text alignment.
  

Duration Modelling in HMMs

• Nelly Suaudeau, Régine André-Obrecht:
  Sound duration modelling and time-variable speaking rate in a speech recognition system.
  
• M. Jones, Philip C. Woodland:
  Using relative duration in large vocabulary speech recognition.
  
• Yifan Gong, William C. Treurniet:
  Duration of phones as function of utterance length and its use in automatic speech recognition.
  
• M. E. Forsyth, Mervyn A. Jack:
  Duration modelling and multiple codebooks in semi-continuous HMMs for speaker verification.
  
• Mike Hochberg, Harvey F. Silverman:
  Constraining model duration variance in HMM-based connected-speech recognition.
  

Speaker Adaptation and Normalization

• Christine Tuerk, Tony Robinson:
  A new frequency shift function for reducing inter-speaker variance.
  
• Yoshio Ono, Hisashi Wakita, Yunxin Zhao:
  Speaker normalization using constrained spectra shifts in auditory filter domain.
  
• Yunxin Zhao:
  Self-learning speaker adaptation based on spectral variation source decomposition.
  
• Tetsuo Kosaka, Edward Willems, Jun-ichi Takami, Shigeki Sagayama:
  A dynamic approach to speaker adaptation of hidden Markov networks for speech recognition.
  
• Lars Knohl, Ansgar Rinscheid:
  Speaker normalization and adaptation based on feature-map projection.
  

Speech Analysis, Articulatory Modelling

• Marcel de Leeuw, Jean Caelen:
  Pitch synchronous calculation of acoustic cues using a cochlea model.
  
• Steve McLaughlin, Andrew Lowry:
  Nonlinear dynamical systems concepts in speech analysis.
  
• Arno J. Klaassen:
  Grouping of acoustical events using cable neurons and the theory of neuronal group selection.
  
• I. R. Gransden, Steve W. Beet:
  Computationally efficient methods of calculating instantaneous frequency for auditory analysis.
  
• Francesco Cutugno, Pietro Maturi:
  Analysing connected speech with wavelets: some Italian data.
  
• Krzysztof Marasek:
  Speech transients analysis using AR-smoothed wigner-ville distribution.
  
• Michel Pitermann, Jean Caelen:
  Comparison of the variability of formants and formant targets using dynamic modeling.
  
• Jean Schoentgen, Zoubir Azami:
  Pitch-synchronous formant extraction by means of a compound auto-regressive model.
  
• Bernard Teston:
  A new air flowmeter design for the investigation of speech production.
  
• Emanuela Magno Caldognetto, Kyriaki Vagges, Giancarlo Ferrigno, Claudio Zmarich:
  Articulatory dynamics of lips in Italian /'vpv/ and /'vbv/ sequences.
  
• Ahmed M. Elgendy:
  Restricted distribution of pharyngeal segments: acoustical or mechanical constraints?
  
• Yohan Payan, Pascal Perrier:
  Vowel normalization by articulatory normalization first attemps for vowel transitions.
  
• Nobuhiro Miki, Naohisa Kamiyama, Nobuo Nagai:
  Synthesis and analysis of vocal source with vibration of larynx.
  
• Imad Znagui, Sami Boudelaa:
  Towards an acoustic-phonetic classification of modern standard arabic vowels.
  
• Alain Marchal, Christine Meunier:
  Divers' speech: variable encoding strategies.
  
• L. Aguilar, B. Blecua, M. Machuca, R. Mann:
  Phonetic reduction processes in spontaneous speech.
  
• N. R. Ganguli:
  Spectral characteristics of fricative sound.
  
• Jean-François Bonastre, Henri Meloni:
  Automatic speaker recognition and analytic process.
  
• Danielle Duez:
  Second formant locus-nucleus patterns in French and Swedish.
  
• Christine Meunier:
  Temporal organisation of segments and sub-segments in consonant clusters.
  
• Abdelkader Bétari, Rémy Bulot:
  Automatic recognition of arabic stop consonants.
  
• M. Inés Torres, P. Iparraguirre:
  Acoustic-phonetic decoding of Spanish occlusive consonants.
  
• Philip Christov:
  Normalized vowel system representation for comparative phonetic studies.
  
• Cécile Thilly:
  Influence of prevocalic consonant on vowel duration in French CV[p] utterances.
  
• Peter E. Czigler:
  Temporal variation in consonant clusters in Swedish.
  
• Wiktor Jassem:
  Discriminant analysis of continuous consonantal spectra.
  

Prosody: Rhythm, Style, Emotion

• Edmund Rooney, Miriam Eckert, Steven M. Hiller, Rebecca Vaughan, John Laver:
  Training consonants in a computer-aided system for pronunciation teaching.
  
• Andrej Miksic, Bogomir Horvat:
  Rhythm analysis of speech and music signals.
  
• Gitta P. M. Laan, Dick R. van Bergem:
  The contribution of pitch contour, phoneme durations and spectral features to the character of spontaneous and read aloud speech.
  
• Juan M. Garrido, Joaquim Llisterri, Carme de la Mota, Antonio Rios:
  Prosodic differences in reading style: isolated vs. contextualized sentences.
  
• Jean Vroomen, René Collier, Sylvie J. L. Mozziconacci:
  Duration and intonation in emotional speech.
  

Improved Algorithms for HMMs

• C. M. Ayer, Melvyn J. Hunt, D. M. Brookes:
  A discriminatively derived linear transform for improved speech recognition.
  
• Marco Saerens:
  Hidden Markov models assuming a continuous-time dynamic emission of acoustic vectors.
  
• Saeed Vaseghi, P. N. Conner, Ben P. Milner:
  Speech modelling using cepstral-time feature matrices.
  
• Yoshiharu Abe, Kunio Nakajima:
  A bounded transition hidden Markov model for continuous speech recognition.
  
• Ami Moyal, Arnon Cohen:
  Speaker independent phoneme recognition using a heuristic search.
  
• Fritz Class, Alfred Kaltenmeier, Peter Regel-Brietzmann:
  Optimization of an HMM - based continuous speech recognizer.
  
• Marco Saerens, Hervé Bourlard:
  Linear and nonlinear prediction for speech recognition with hidden Markov models.
  
• M. N. Lokbani, Denis Jouvet, Jean Monné:
  Segmental post-processing of the n-best solutions in a speech recognition system.
  
• Tatsuo Matsuoka, Chin-Hui Lee:
  A study of on-line Bayesian adaptation for HMM-based speech recognition.
  
• B. A. Maxwell, Philip C. Woodland:
  Hidden Markov models using shared vector linear predictors.
  

Noisy Speech and Enhancement

• Maurizio Omologo, Piergiorgio Svaizer:
  Talker localization and speech enhancement in a noisy environment using a microphone array based acquisition system.
  
• Takao Kobayashi, Toshio Kanno, Satoshi Imai:
  Generalized cepstral modeling of speech degraded by additive noise.
  
• Stelios Bakamidis, George Carayannis:
  Noise quality improvement through SVD equalization.
  
• Fei Xie, Dirk Van Compernolle:
  Speech enhancement by nonlinear spectral estimation - a unifying approach.
  
• Kristian Kroschel, Keld Lange:
  Subband array processing for speech enhancement.
  

Speaker Variability

• Vincent Pean, Sheila M. Williams, Maxine Eskenazi:
  The design and recording of icy, a corpus for the study of intraspeaker variability and the characterisation of speaking styles.
  
• Andrej Ljolje:
  Speaker clustering for improved speech recognition.
  
• Henk van den Heuvel, Bert Cranen, A. C. M. Rietveld:
  Speaker-variability in spectral bands of dutch vowel segments.
  
• Shuichi Itahashi, Kimihito Tanaka:
  A method of classification among Japanese dialects.
  
• J. Antonio Hernández-Méndez, Aníbal R. Figueiras-Vidal:
  Measuring similarities among speakers by means of neural networks.
  

Segmentation and Labelling

• Maria Rangoussi, Stylianos Bakamidis, George Carayannis:
  Robust endpoint detection of speech in the presence of noise.
  
• Bianca Angelini, Fabio Brugnara, Daniele Falavigna, Diego Giuliani, Roberto Gretter, Maurizio Omologo:
  Automatic segmentation and labeling of English and Italian speech databases.
  
• Azarshid Farhat, Guy Perennou, Régine André-Obrecht:
  A segmental approach versus a centisecond one for automatic phonetic time-alignment.
  
• I. Heroaez, J. Barandiaran, Enrique Monte, Borja Etxebarria:
  A segmentation algorithm based on acoustical features using a self organizing neural network.
  
• Piero Cosi:
  SLAM: segmentation and labelling automatic module.
  
• Christian Heise, Hans-Heinrich Bothe:
  Phone and syllable segmentation by concurrent window modules.
  
• Barbara Eisen:
  Reliability of speech segmentation and labelling at different levels of transcription.
  
• Dick R. van Bergem:
  On the perception of acoustic and lexical vowel reduction.
  
• Brit van Ooyen, Anne Cutler, Pier Marco Bertinetto:
  Click detection in Italian and English.
  
• Andrew R. Nix, M. Gareth Gaskell, William D. Marslen-Wilson:
  Phonological variation and mismatch in lexical access.
  
• Monique van Zon, Béatrice de Gelder:
  Perception of word boundaries by dutch listeners.
  
• Anne Bonneau, Linda Djezzar, Yves Laprie:
  Perception of French stop bursts, implications for stop identification.
  
• Zdravko Kacic, Bogomir Horvat:
  Using isofrequency neural column for harmonic sound scene decomposition.
  
• A. K. Datta:
  Do ear perceive vowel through formants?
  
• Trupti Vyas, Michael J. Pont, Seyed J. Mashari:
  Speech recognition using auditory models and neural networks.
  
• Changxue Ma, Armin Kohlrausch:
  The influence of temporal processes on spectral masking patterns of harmonic complex tones and vowels.
  
• Hisao Kuwabara:
  Temporal effect on the perception of continuous speech and a possible mechanism in the human auditory system.
  
• Edward Jones, Eliathamby Ambikairajah:
  Comparison of various adaptation mechanisms in an auditory model for the purpose of speech processing.
  
• I. A. Vartanian, Tatiana V. Chernigovskaya:
  Sensory-motor manifestations of speech-hearing interaction.
  
• Tatiana V. Chernigovskaya, I. A. Vartanian, T. I. Tokareva:
  Syllable perception: lateralization of native and foreign languages.
  
• Michael J. Pont:
  Simulation of short-latency auditory evoked potentials: a pilot study.
  
• Regine Kolinsky, Jose Morais:
  Intermediate representations in spoken word recognition: a cross-linguistic study of word illusions.
  
• Jianfen Cao:
  Time - varing manner on formant trajectories of Chinese diphthongs.
  
• Yifan Gong, Jean Paul Haton:
  Iterative transformation and alignment for speech labeling.
  
• Kai Hübener, Andreas Hauenstein:
  Controlling search in segmentation lattices of speech signals.
  
• Hiroshi Shimodaira, Mitsuru Nakai:
  Accent phrase segmentation using transition probabilities between pitch pattern templates.
  
• Wolfgang Reichl, Günther Ruske:
  Syllable segmentation of continuous speech with artificial neural networks.
  
• Mats Blomberg, Rolf Carlson:
  Labelling of speech given its text representation.
  

Prosody: Analysis and Modelling of <i>F</i>₀ Contours

• Louis ten Bosch:
  On the automatic classification of pitch movements.
  
• U. Jensen, Roger K. Moore, Paul Dalsgaard, Børge Lindberg:
  Modelling of intonation contours at the sentence level using CHMMs and the 1961 o'connor and arnold scheme.
  
• Paul Taylor:
  Automatic recognition of intonation from F₀ contours using the rise/fall/connection model.
  
• Edouard Geoffrois:
  A pitch contour analysis guided by prosodic event detection.
  
• Grazyna Demenko, Ignacy Nowak, Janusz Imiolczyk:
  Analysis and synthesis of pitch movements in a read polish text.
  

Speech Recognition in Noise

• William A. Ainsworth, Georg F. Meyer:
  Noise adaptation: speech recognition by auditory models and human listeners.
  
• J. A. Nolazco Flores, Steve J. Young:
  Adapting a HMM-based recogniser for noisy speech enhanced by spectral subtraction.
  
• Tetsunori Kobayashi, Ryuji Mine, Katsuhiko Shirai:
  Speech recognition under the unstationary noise based on the noise Markov model and spectral-subtraction.
  
• M. J. F. Gales, Steve J. Young:
  HMM recognition in noise using parallel model combination.
  
• Laurent Buniet, Dominique Fohr, Yolande Anglade, Jean-Claude Junqua, Jean-Marie Pierrel:
  Selectively trained neural networks for connected word recognition in noisy environments.
  

Speaker Independency

• Bianca Angelini, Fabio Brugnara, Daniele Falavigna, Diego Giuliani, Roberto Gretter, Maurizio Omologo:
  A baseline of a speaker independent continuous speech recognizer of Italian.
  
• Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael Picheny:
  Word lookahead scheme for cross-word right context models in a stack decoder.
  
• David B. Grayden, Michael S. Scordilis:
  Recognition of obstruent phonemes in speaker-independent fluent speech using a hierarchical approach.
  
• Bernd Plannerer, Günther Ruske:
  A continuous speech recognition system using phonotactic constraints.
  

Speech Synthesis

• M. Ouadou, A. Rajouani, M. Zyoute, J. Rosenfeld, M. Najim:
  Joint arabic-hebrew speech synthesis system.
  
• Eduardo López Gonzalo, Gábor Olaszy, Géza Németh:
  Improvements of the Spanish version of the multivox text-to-speech system.
  
• Mats Ljungqvist, Hiroya Fujisaki:
  Generating intonation for Swedish text-to-speech conversion using a quantitative model for the F₀ contour.
  
• Peter Meyer, Hans-Wilhelm Rühl, R. Krüger, M. Kugler, L. Vogten, A. Dirksen, Karim Belhoula:
  PHRITTS - a text-to-speech synthesizer for the German language.
  
• Karim Belhoula:
  Rule-based grapheme-to-phoneme conversion of names.
  
• Iain R. Murray, Morag M. Black:
  A prototype text-to-speech system for scottish gaelic.
  
• Janusz Imiolczyk, Ignacy Nowak, Grazyna Demenko:
  A text-to-speech system for polish.
  
• Marian J. Macchi, Mary Jo Altom, Dan Kahn, Sharad Singhal, Murray F. Spiegel:
  Intelligibility as a function of speech coding method for template-based speech synthesis.
  
• Maggie Gaved:
  Pronunciation and text normalisation in applied text-to-speech systems.
  
• Jill House, Catriona MacDermid, Scott McGlashan, Andrew Simpson, Nick J. Youd:
  Evaluating synthesised prosody in simulations of an automated telephone enquiry service.
  
• Katherine Morton, Marcel Tatham:
  Speech synthesis in dialogue systems.
  
• Elissaveta Abadjieva, Iain R. Murray, John L. Arnott:
  Applying analysis of human emotional speech to enhance synthetic speech.
  
• Eric Lewis, Marcel Tatham:
  A generic front end for text-to-speech synthesis systems.
  
• Robert W. P. Luk, Robert I. Damper:
  Experiments with silent-e and affix correspondences in stochastic phonographic transduction.
  
• Georg Fries:
  Phoneme-dependent speech synthesis in the time and frequency domains.
  
• Inger Karlsson, Lennart Neovius:
  Speech synthesis experiments with the glove synthesiser.
  
• Volker Kraft:
  Auditory detection of discontinuities in synthesis-by-concatenation.
  
• Yun-Keun Lee, Seung-Kwon Ahn:
  Effects of the phase jitters on naturalness of synthesized speech.
  
• Briony Williams:
  Letter-to-sound rules for the welsh language.
  

Dialogue Structure

• Christel Müller, Fred Runge:
  Dialogue design principles - key for usability of voice processing.
  
• Hans Dybkjær, Niels Ole Bernsen, Laila Dybkjær:
  Wizard-of-oz and the trade-off between naturalness and recogniser constraints.
  
• Cerian Jones, Roberto Garigliano:
  Dialogue analysis and generation: a theory for modelling natural English dialogue.
  
• Catriona MacDermid:
  Features of naive callers' dialogues with a simulated speech understanding and dialogue system.
  
• Fabrice Duermael, Bertrand Gaiffe:
  Refering to actions in man-machine command dialogues.
  
• Yoichi Yamashita, Riichiro Mizoguchi:
  Next utterance prediction based on two kinds of dialog models.
  
• T. Andemach, G. Deville, Luc Mortier:
  The design of a real world wizard of oz experiment for a speech driven telephone directory information system.
  
• Sheryl R. Young:
  Dialog structure and plan recognition in spontaneous spoken dialog.
  
• Julia Hirschberg, Christine H. Nakatani:
  A speech-first model for repair identification in spoken language systems.
  
• Sheryl R. Young, Wayne H. Ward:
  Recognition confidence measures for spontaneous spoken dialog.
  

Language Modelling

• R. Zhao, Patrick Kenny, P. Labute, Douglas D. O'Shaughnessy:
  Issues in large scale statistical language modeling.
  
• Roberto Garigliano, Kevin Johnson, Russell J. Collingham:
  A data-driven case for a spontaneous speech grammar.
  
• Reinhard Kneser, Hermann Ney:
  Improved clustering techniques for class-based statistical language modelling.
  
• Jeremy H. Wright, Gareth J. F. Jones, Harvey Lloyd-Thomas:
  A consolidated language model for speech recognition.
  
• Michael K. McCandless, James R. Glass:
  Empirical acquisition of word and phrase classes in the atis domain.
  
• Tung-Hui Chiang, Keh-Yih Su:
  The effects of parameter smoothing on robust learning in syntactic ambiguity resolution.
  
• Enrique Vidal, Roberto Pieraccini, Esther Levin:
  Learning associations between grammars: a new approach to natural language understanding.
  
• Michèle Jardino, Gilles Adda:
  Language modelling for CSR of large corpus using automatic classification of words.
  
• Helmut Lucke:
  Inference of stochastic context-free grammar rules from example data using the theory of Bayesian belief propagation.
  
• Petra Witschel:
  Constructing linguistic oriented language models for large vocabulary speech recognition.
  

Prosody: Prosodic Parameter Manipulation

• Eduardo Rodríguez Banga, Carmen García-Mateo:
  New frequency domain prosodic modification techniques.
  
• H. D. Wang, D. Degryse, Fabrizio Carrara:
  A prosody modification approach for auditory user feedback in the spell pronunciation teaching system.
  
• Tohru Takagi, Eiichi Miyasaka:
  A speech prosody conversion system with a high quality speech analysis-synthesis method.
  
• Marc Swerts, René Collier:
  On the perceived serial position of discourse units.
  
• Paul C. Bagshaw, Steven M. Hiller, Mervyn A. Jack:
  Enhanced pitch tracking and the processing of F₀ contours for computer aided intonation teaching.
  

New Architectures for Neural Networks

• Chakib Tadj, Franck Poirier:
  Improved DVQ algorithm for speech recognition: a new adaptive learning rule with neurons annihilation.
  
• Taro Sasaki, Tadashi Kitamura, Akira Iwata:
  Speaker-independent 212 word recognition using combNET-II.
  
• M. Asunción Castaño, Enrique Vidal, Francisco Casacuberta:
  Learning direct acoustic-to-semantic mappings through simple recurrent networks.
  

Noise Reduction and Channel Adaption

• Saeed Vaseghi, Ben P. Milner:
  Noise-adaptive hidden Markov models based on wiener filters.
  
• K. F. Wong, S. H. Leung, H. C. Ng:
  Noisy speech recognition using singular value decomposition and two-sided linear prediction.
  
• Franck Martin, Kiyohiro Shikano, Yasuhiro Minami:
  Recognition of noisy speech by composition of hidden Markov models.
  
• Yuqing Gao, Jean Paul Haton:
  Noise reduction and speech recognition in noise conditions tested on LPNN-based continuous speech recognition system.
  
• Michael Trompf, Ralf Richter, Harald Eckhardt, Heidi Hackbarth:
  Combination of distortion-robust feature extraction and neural noise reduction for ASR.
  
• Chafic Mokbel, Jean Monné, Denis Jouvet:
  On-line adaptation of a speech recognizer to variations in telephone line conditions.
  
• Matthias Wittmann, Otto Schmidbauer, Abdulmesih Aktas:
  Online channel compensation for robust speech recognition.
  
• Patrice Alexandre, Jérôme Boudy, Philip Lockwood:
  Evaluation of car noise reduction/compensation techniques for digit recognition in a speaker-independent context.
  
• A. Brancaccio, C. Pelaez:
  Experiments on noise reduction techniques with robust voice detector in car environment.
  

Word Spotting

• Satoshi Nakamura, Toshio Akabane, Seiji Hamaguchi:
  Robust word spotting in adverse car environments.
  
• Richard C. Rose:
  Definition of subword acoustic units for wordspotting.
  
• Jiro Kiyama, Yoshiaki Itoh, Ryuichi Oka:
  Spontaneous speech recognition by sentence spotting.
  
• Philippe Jeanrenaud, Kenney Ng, Man-Hung Siu, Jan Robin Rohlicek, Herbert Gish:
  Phonetic-based word spotter: various configurations and application to event spotting.
  
• Akihiro Imamura, Mikio Kitai:
  An application of word-spotting in a voice activated service entry system.
  
• Eduardo Lleida, José B. Mariño, Josep M. Salavedra, Antonio Bonafonte, Enrique Monte, A. Martinez:
  Out-of-vocabulary word modelling and rejection for keyword spotting.
  
• Mary O'Kane, P. E. Kenne:
  Word and phrase spotting with limited training.
  
• Jean-Marc Boite, Hervé Bourlard, Bart D'hoore, Marc Haesen:
  A new approach towards keyword spotting.
  
• J. Alvarez-Cercadillo, Luis A. Hernandez-Gomez:
  Grammar learning and word spotting using recurrent neural networks.
  
• Shigeki Okawa, Tetsunori Kobayashi, Katsuhiko Shirai:
  Word spotting in conversational speech based on phonemic unit likelihood by mutual information criterion.
  

Speech Processing and Coding

• F. Dohnal:
  Generalized frequency domain adaptive filter for acoustic echo canceller.
  
• Joel Crestel, Michel Guitton:
  Estimation of speech signal classification features in a simulated hyperbaric environment.
  
• Petr Pollák, Pavel Sovka, Jan Uhlír:
  Noise suppression system for a car.
  
• Peter Heitkämper, Michael Walker II:
  Adaptive gain control and echo cancellation for hands-free telephone systems.
  
• W. Nick Campbell:
  Predicting segmental durations for accommodation within a syllable-level timing framework.
  
• Tore Fjällbrant, Fisseha Mekuria, Shahrokh Amirijoo:
  A filtersank based on physiologically measured characteristics in an auditory model for speech signal processing.
  
• Fu-Rong Jean, Chih-Chung Kuo, Hsiao-Chuan Wang:
  Spectral sensitivity weighted transform coding for LSP parameters.
  
• Rainer Martin:
  An efficient algorithm to estimate the instantaneous SNR of speech signals.
  
• Laurent Mauuary, Jean Monné:
  Speech/non-speech detection for voice response systems.
  
• Alexander Osipov, Vladimir Zentsov:
  Time-spectral approach to compiling speech reconstruction.
  
• J. A. Haigh, John S. Mason:
  A voice activity detector based on cepstral analysis.
  
• Jrgen Paulus, Christiane Antweiler, Christian G. Gerlach:
  High quality coding of wideband speech at 24 kbit/s.
  
• H. Dia, Gang Feng, Yannick Mahieux:
  A 32 kbit/s wideband speech coder based on transform coding.
  
• Oded Gottesman, Yair Shoham:
  Realtime implementation of high-quality 32 kbps wideband LD-CELP coder.
  
• A. Popescu, D. Vicard, F. Druilhe:
  A fixed-point implementation of the 16 kb/s LD-CELP speech coding algorithm.
  
• Christian G. Gerlach:
  Optimality of sequential quantization in analysis-by-synthesis speech codecs.
  
• Radwan Kastantin, Gang Feng:
  A sub-band MPLPC coder for high quality speech coding at 16 kbit/s.
  
• Enzo Mumolo, Alessio Rebelli:
  Optimal multepulse excitation determination by simulated annealing.
  
• K. W. Law, C. F. Chan:
  Split vector quantization of the LPC parameters using weighted lattice structure.
  
• Stefan Bruhn:
  A new approach to noiseless interframe coding of LPC parameters in vector quantizer applications.
  
• Torbjørn Svendsen:
  Efficient quantization of speech spectral information.
  
• Stefan Feldes:
  Enhancing robustness of coded LPC-spectra to channel errors by use of residual redundancy.
  
• S. A. Atungsiri, Ahmet M. Kondoz, Barry G. Evans:
  Multi-rate source and channel coding for mobile communication systems.
  
• Takehiro Moriya, Satoshi Miki, Kazunori Mano, Hitoshi Ohmuro:
  Training method of the excitation codebook for CELP.
  

Prosody: Phrasing

• Gösta Bruce, Björn Granström, Kjell Gustafson, David House:
  Phrasing strategies in prosodic parsing and speech synthesis.
  
• Eva Strangert, Bo Strangert:
  Prosody in the perception of syntactic boundaries.
  
• Jan-Roelof de Pijper, Angelien Sanderman:
  Prosodic cues to the perception of constituent boundaries.
  
• Esther Grabe, Tara Hoist, Francis Nolan, Paul Warren:
  Acoustic cues to syntactic structure - evidence from prosodic and segmental effects.
  
• Frédéric Beaugendre, Anne Lacheret-Dujour:
  Automatic generation of French intonation based on a perceptual study and morpho-syntactic information.
  

MLPs and TDNNs for Speech Recognition

• Stephen A. Zahorian, Zaki B. Nossair, Claude A. Norton III:
  A partitioned neural network approach for vowel classification using smoothed time/frequency features.
  
• Tadashi Kitamura:
  Speaker-independent 100 word recognition using dynamic spectral features of speech and a neural network.
  
• Ming Zhu, Klaus Fellbaum:
  Speaker independent isolated word recognition using vector quantization and neural networks.
  
• Kjell Elenius, Hans G. C. Traven:
  Multi-layer perceptrons and probabilistic neural networks for phoneme recognition.
  
• C. S. Blackburn, Julie Vonwiller, R. W. King:
  Automatic accent classification using artificial neural networks.
  
• Mark Huckvale:
  The benefits of tiered segmentation for the recognition of phonetic properties.
  
• David Lubensky:
  Generalized context-dependent phone modeling using artificial neural networks.
  
• Hermann Hild, Alex Waibel:
  Speaker-independent connected letter recognition with a multi-state time delay neural network.
  
• Ulrich Bodenhausen, Alex Waibel:
  Tuning by doing: flexibility through automatic structure optimization.
  
• Christoph Windheuser, Frédéric Bimbot:
  Phonetic features for spelled letter recognition with a time delay neural network.
  
• Veronika Bappert, Matthias Jobst:
  Training of a time-delay neural network for speech recognition by solving stiff differential equations.
  

Speech Translation, Language Identification, Parsers

• Shigeki Sagayama, Jun-ichi Takami, Akito Nagai, Harald Singer, Kouichi Yamaguchi, Kazumi Ohkura, Kenji Kita, Akira Kurematsu:
  ATREUS: a speech recognition front-end for a speech translation system.
  
• Tsuyoshi Morimoto, Toshiyuki Takezawa, Fumihiro Yato, Shigeki Sagayama, Toshihisa Tashiro, Masaaki Nagata, Akira Kurematsu:
  ATR's speech translation system: ASURA.
  
• Monika Woszczyna, Noah Coccaro, A. Eisele, Alon Lavie, Arthur E. McNair, Thomas Polzin, Ivica Rogina, Carolyn Penstein Rosé, Tilo Sloboda, M. Tomita, J. Tsutsumi, N. Aoki-Waibel, Alex Waibel, Wayne H. Ward:
  Recent advances in JANUS: a speech translation system.
  
• Manny Rayner, Ivan Bretan, David M. Carter, Michael Collins, Vassilios Digalakis, Björn Gambäck, Jaan Kaja, Jussi Karlgren, Bertil Lyberg, Stephen G. Pulman, Patti Price, Christer Samuelsson:
  Spoken language translation with MID-90's technology: a case study.
  
• Timothy J. Hazen, Victor W. Zue:
  Automatic language identification using a segment-based approach.
  
• Yeshwant K. Muthusamy, Kay M. Berkling, Takayuki Arai, Ronald A. Cole, Etienne Barnard:
  A comparison of approaches to automatic language identification using telephone speech.
  
• Ying Cheng, Yves Normandin, Paul Fortier:
  Integration of neural networks and robust parsers in natural language understanding.
  
• Pierre Dauchy, Christophe Mignot, Claude Valot:
  Joint speech and gesture analysis some experimental results on multimodal interface.
  
• Keikichi Hirose, Yasuharu Asano:
  Generation of speech reply in the speech response system.
  
• Evangelos Dermatas, George Kokkinakis:
  A fast multilingual probabilistic tagger.
  
• Jin'ichi Murakami, Hiroki Yamatomo, Shigeki Sagayama:
  The possibility for acquisition of statistical network grammar using ergodic HMM.
  
• Evelyne Millien, Roland Kuhn:
  A robust analyzer for spoken language understanding.
  
• R. T. Dutton, John C. Foster, Mervyn A. Jack, F. W. M. Stentiford:
  Identifying usability attributes of automated telephone services.
  
• Andrew Hunt:
  Utilising prosody to perform syntactic disambiguation.
  
• Steven M. Hiller, Edmund Rooney, Jean-Paul Lefèvre, Mervyn A. Jack:
  Spell: an automated system for computer-aided pronunciation teaching.
  
• Edmund Rooney, Rebecca Vaughan, Steven M. Hiller, Fabrizio Carraro, John Laver:
  Training vowel pronunciation using a computer-aided teaching system.
  
• Mary Zajicek, Ken Brownsey:
  Methods for traversing a pre-recorded speech message network to optimise dialogue in telephone answering systems.
  
• Roger Hanes, Jo Salter, Paul Popay, Frances Hedley:
  Service creation tools for creating speech interactive services.
  
• Julia Hirschberg, Jacques M. B. Terken:
  Deaccentuation and persistence of grammatical function and surface position.
  
• Stefan Euler, K. Riedel:
  Design and implementation of a speech server for unix based multimedia applications.
  
• David Goodine, Victor W. Zue:
  Romaine: a lattice based approach to lexical access.
  
• Toffee A. Albina, Erica G. Bernstein, David M. Goblirsch, Douglas E. Lake:
  A system for clustering spoken documents.
  

Dialogue Evalution

• Nathalie A. Vergeynst, Keith Edwards, John C. Foster, Mervyn A. Jack:
  Spoken dialogues for human-computer interaction over the telephone: complexity measures.
  
• Lynette Hirschman, Christine Pao:
  The cost of errors in a spoken language system.
  
• Andrew Simpson, Norman M. Eraser:
  Black box and glass box evaluation of the SUNDIAL system.
  
• Cristina Delogu, Andrea Di Carlo, Ciro Sementina, Silvia Stecconi:
  A methodology for evaluating human-machine spoken language interaction.
  
• Philippe Morin, Jean-Claude Junqua:
  Error correction and ambiguity resolution in multimodal man-machine dialogue.
  

Data Bases

• Marie-Franoise Castaing, Dominique True-Martini:
  Analysis of the speaker and operator behaviours.
  
• Alix de Ginestel-Mailland, Martine de Calmès, Guy Perennou:
  Multi-level transcription of speech corpora from orthographic forms.
  
• Andrej Ljolje, Michael D. Riley:
  Automatic segmentation of speech for TTS.
  
• Olivier Boëffard, B. Cherbonnel, F. Emerard, S. White:
  Automatic segmentation and quality evaluation of speech unit inventories for concatenation-based, multilingual PSOLA text-to-speech systems.
  

Letter to Sound and Architecture for TTS

• Bert Van Coile:
  On the development of pronunciation rules for text-to-speech synthesis.
  
• Walter Daelemans, Antal van den Bosch:
  Tabtalk: reusability in data-oriented grapheme-to-phoneme conversion.
  
• Anders Lindström, Mats Ljungqvist, Kjell Gustafson:
  A modular architecture supporting multiple hypotheses for conversion of text to phonetic and linguistic entities.
  
• Jon P. Iles, William H. Edmondson:
  The use of a non-linear model for text-to-speech conversion.
  

Perception

• Astrid van Wieringen, John K. Cullen, Louis C. W. Pols:
  The perceptual relevance of CV- and VC- transitions in identifying stop consonants: cross-language results.
  
• Vincent J. van Heuven, Willy Jongenburger:
  Perceptual effects of place and voicing assimilation in dutch consonants.
  
• Brit van Ooyen:
  Detection of vowels and consonants by human listeners: effects of minimising auditory memory load.
  
• Gérard Bailly:
  Resonances as possible representation of speech in the auditory-to-articulatory transform.
  
• Rob Goedemans, Vincent J. van Heuven:
  A perceptual explanation of the weightlessness of the syllable onset.
  

Search Algorithms

• Enrico Bocchieri:
  A study of the beam-search algorithm for large vocabulary continuous speech recognition and methods for improved efficiency.
  
• Lorenzo Fissore, Egidio P. Giachin, Pietro Laface, P. Massafra:
  Using grammars in forward and backward search.
  
• Gernot A. Fink, Franz Kummert, Gerhard Sagerer, Bernd Seestaedt:
  Robust interpretation of speech.
  
• I. Lee Hetherington, Michael S. Phillips, James R. Glass, Victor W. Zue:
  A* word network search for continuous speech recognition.
  
• Roxane Lacouture, Yves Normandin:
  Efficient lexical access strategies.
  

Speech Recognition, HMMs, NNs

• M. Inés Torres, Francisco Casacuberta:
  Multiple codebook Spanish phone recognition using semicontinuous hidden Markov models.
  
• Antonio Bonafonte, Xavier Ros, Jose B. Marifio:
  An efficient algorithm to find the best state sequence in HSMM.
  
• Alex Acero, C. Crespo, C. de la Torre, Juan Carlos Torrecilla:
  Robust HMM-based endpoint detector.
  
• Isabel Galiano, Francisco Casacuberta:
  Experiments on Spanish phone recognition using automatically derived phonemic baseforms.
  
• Seiichi Nakagawa, Hideyuki Suzuki, Li Zhao:
  Evaluation of VQ-distortion based HMM.
  
• Jianming Song:
  Continuous HMM for word spotting and rejection of non vocabulary word in speech recognition over telephone networks.
  
• Qiang Huo, Chorkin Chan, Chin-Hui Lee:
  Bayesian learning of the parameters of discrete and tied mixture HMMs for speech recognition.
  
• Gernot A. Fink, Franz Kummert, Gerhard Sagerer, Ernst Günter Schukat-Talamazzini:
  Speech recognition using semantic hidden Markov networks.
  
• Simon Downey, Martin Russell, Peter Nowell, David Bijl, Kirsta Galloway, Keith Ponting:
  Experiments in vocabulary independent speech recognition using phoneme decision trees.
  
• M. J. F. Gales, Steve J. Young:
  Segmental hidden Markov models.
  
• Xue Wang, Louis ten Bosch, Louis C. W. Pols:
  Impact of dimensionality and correlation of observation vectors in HMM-based speech recognition.
  
• Fritz Class, Alfred Kaltenmeier, Peter Regel-Brietzmann:
  Evaluation of an HMM speech recognizer with various continuous speech databases.
  
• Adam Wrzoskowicz:
  Hidden Markov models for noisy speech recognition.
  
• Dionysis E. Tsoukalas, J. Mourjopoulos, George Kokkinakis:
  Neural network speech enhancer utilizing masking properties.
  
• Maria J. Castro, Juan C. Perez:
  Comparison of geometric, connections and structural techniques on a difficult isolated word recognition task.
  
• A. Mellouk, Patrick Gallinari, F. Rauscher:
  Prediction and discrimination in neural networks for continuous speech recognition.
  
• Shuping Ran, J. Bruce Millar:
  Two schemes of phonetic feature extraction using artificial neural networks.
  
• Bojan Petek, Anuska Ferligoj:
  On use of discriminant analysis in predictive connectionist speech recognition.
  
• N. H. Russell, Frank Fallside, Richard W. Prager:
  Non-linear time compression for lexical access.
  
• Richard Brierton, Nigel Sedgwick:
  Talker enrollment for speech recognition by synthesis.
  
• Kazuya Takeda, Naomi Inoue, Shingo Kuroiwa, Tomohiro Konuma, Seiichi Yamamoto:
  Improving robustness of network grammar by using class HMM.
  
• J. A. Elliott, M. E. Forsyth, Fergus R. McInnes, N. W. Ramsey:
  Parallelising k-means clustering on distributed memory MIMD computers.
  
• P. Berenyi, Klára Vicsi:
  On the proper sub-word unit inventory for CSR.
  
• Li Deng, Don Sun:
  Speech recognition using the atomic speech units constructed from overlapping articulatory features.
  
• Olivier Siohan, Yifan Gong, Jean Paul Haton:
  A Bayesian approach to phone duration adaptation for lombard speech recognition.
  
• Javier Hernando, José B. Mariño, Climent Nadeu:
  Multiple multilabeling to improve HMM-based speech recognition in noise.
  
• Lutoslawa Richter, Piotr Domagaia:
  Discrimination of polish stop consonants based on mapped techniques.
  

Spoken Language Dialogue

• Wieland Eckert, Scott McGlashan:
  Managing spoken dialogues for information services.
  
• Paul Heisterkamp:
  Ambiguity and uncertainty in spoken dialogue.
  
• Elisabetta Gerbino, Morena Danieli:
  Managing dialogue in a continuous speech understanding system.
  
• Pierre Lefebvre, G. Duncan, Frank Poirier:
  Speaking with computers: a multimodal approach.
  
• Philippe Morin, Jean-Claude Junqua:
  Habitable interaction in goal-oriented multimodal dialogue systems.
  

Speech Input/Output Assessment

• Jorn Stern Nielsen, Bo Baungaard:
  Test of voice quality on ATM based equipment.
  
• Harald Klaus, H. Klix, Jochem Sotscheck, Klaus Fellbaum:
  An evaluation system for ascertaining the quality of synthetic speech based on subjective category rating tests.
  
• Arnd Mariniak:
  A global framework for the assessment of synthetic speech without subjects.
  
• Lennart Neovius, Parimala Raghavendra:
  Comprehension of KTH text-to-speech with "listening speed" paradigm.
  
• Hans G. Tillmann, Bernd Pompino-Marschall:
  Theoretical principles concerning segmentation, labelling strategies and levels of categorical annotation for spoken language database systems.
  
• Peter J. Wyard:
  The comparative assessment of commercial speech recognisers.
  
• A. Riccio, F. Ceglie, A. Brancaccio:
  Reliable assessment of speech recognisers for telephone environment.
  
• Martine Garnier-Rizet:
  Evaluation of a rule-based text-to-speech system for French at the segmental level.
  
• Cristina Delogu, Andrea Paoloni, Paola Ridolfi, Kyriaki Vagges:
  Intelligibility of speech produced by text-to-speech synthesizers over the orthophonic and telephonic channel.
  
• Murray F. Spiegel:
  Using the ORATOR® synthesizer for a public reverse-directory service: design, lessons, and recommendations.
  

Synthesis: Sound Generation

• Sophie Grau, Christophe d'Alessandro, Gaël Richard:
  A speech formant synthesizer based on harmonic + random formant-waveforms representations.
  
• Alexander G. Hauptmann:
  SPEAKEZ: a first experiment in concatenation synthesis from a large corpus.
  
• Joop Kerkhoff, Lou Boves:
  Designing control rules for a serial pole-zero vocal tract model.
  
• Shin'ya Nakajima:
  English speech synthesis based on multi-layered context oriented clustering; towards multi-lingual speech synthesis.
  
• Christine Tuerk, Tony Robinson:
  Speech synthesis using artificial neural networks trained on cepstral coefficients.
  

Hybrid HMMs/ANNs for Speech Recognition

• Steve Renals, David MacKay:
  Bayesian regularisation methods in a hybrid MLP-HMM system.
  
• P. Schmid, Ronald A. Cole, Mark A. Fanty, Hervé Bourlard, M. Haessen:
  Real-time, neural network-based, French alphabet recognition with telephone speech.
  
• Gerhard Rigoll:
  Joint optimization of multiple neural codebooks in a hybrid connectionist-HMM speech recognition system.
  
• Mikko Kurimo:
  Using LVQ to enhance semi-continuous hidden Markov models for phonemes.
  
• Pablo Aibar, Francisco Casacuberta:
  An improvement of the two-level DP matching algorithm using k-NN techniques for acoustic-phonetic decoding.
  
• Hervé Bourlard, Jean-Marc Boite, Bart D'hoore, Marco Saerens:
  Performance comparison of hidden Markov models and neural networks for task dependent and independent isolated word recognition.
  
• Patrick Haffner:
  Connectionist speech recognition with a global MMI algorithm.
  
• Denys Boiteau, Patrick Haffner:
  Connectionist segmental post-processing of the n-best solutions in isolated and connected word recognition task.
  
• Jean-Pierre Martens, Annemie Vorstermans, Nick Cremelie:
  A new dynamic programming/multi-layer perceptron hybrid for continuous speech recognition.
  
• Tony Robinson, Luís B. Almeida, Jean-Marc Boite, Hervé Bourlard, Frank Fallside, Mike Hochberg, Dan J. Kershaw, Phil Kohn, Yochai Konig, Nelson Morgan, João Paulo Neto, Steve Renals, Marco Saerens, Chuck Wooters:
  A neural network based, speaker independent, large vocabulary, continuous speech recognition system: the WERNICKE project.
  

Visual Cues

• Hans-Heinrich Bothe, Frauke Rieger, Robert Tackmann:
  Visual coarticulation effects in syllable environment.
  
• Christine H. Shadle, John N. Carter, T. P. Monks, J. Field:
  Depth measurement of face and palate by structured light.
  
• Louis-Jean Boë, Sonia Kandel, Annie Chappelet, Tahar Lallouache:
  Visiolab: a multimedia environment for the study of bimodal speech perception.
  
• Jordi Robert-Ribes, Tahar Lallouache, Pierre Escudier, Jean-Luc Schwartz:
  Integrating auditory and visual representations for audiovisual vowel recognition.
  

Telecommunication, Application Aspects

• Bo Baungaard, Jorn Stern Nielsen:
  Speech recognition over packetized voice systems.
  
• I. W. G. Jenkins:
  Voice applications on BT's derived services network.
  
• Jean-Yves Magadur, Frédéric Gavignet, François Andry, Francis Charpentier:
  A French oral dialogue system for flight reservations over the telephone.
  
• Shingo Kuroiwa, Kazuya Takeda, Naomi Inoue, Izuru Nogaito, Seiichi Yamamoto, Makoto Shozakai, Kunihiko Owa, Masahiko Takahashi, Ryuuji Matsumoto:
  A voice-activated extension telephone exchange system.
  
• William C. G. Ortel, Dina Yashchin:
  The VOIS project in retrospect.
  
• Eduardo Lleida, José B. Mariño, Arturo Moreno:
  TELEMACO - a real time keyword spotting application for voice dialling.
  
• Peter J. Wyard:
  The relative importance of the factors affecting recogniser performance with telephone speech.
  
• Thomas Burger, Ulrich Schultheiß:
  A robust acoustic echo canceller for a hands-free voice-controlled telecommunication terminal.
  
• J. E. Hart, Patrick A. Naylor, Oguz Tanrikulu:
  Polyphase allpass IIR structures for sub-band acoustic echo cancellation.
  
• James Monaghan, Christine Cheepen:
  Speech input systems and their effect on written language skills.
  
• Gábor Olaszy, Géza Németh:
  Voxaid: an interactive speaking communication aid software for the speech impaired.
  
• U. Hartmann, K. Hermansen, F. K. Fink:
  Feature extraction for profoundly deaf people.
  
• Alfred Hauenstein:
  Architecture of a 10, 000 word real time speech recognizer.
  
• Thomas Hermann, Harald Eckhardt, Michael Trompf, Heidi Hackbarth:
  A noise-robust real-time word recognition hardware module.
  
• Myoung-Wan Koo:
  KARS: a speaker-independent, vocabulary-independent speech recognition system.
  
• Fergus R. McInnes, J. A. Elliott, N. W. Ramsey, M. E. Forsyth, Andrew M. Sutherland, Mervyn A. Jack:
  A parallel processing keyword recogniser for police national computer enquiries.
  
• Andrea Paoloni, Torbjørn Svendsen, Bernhard Kaspar, Denis Johnston, Gunnar Hult:
  Cost232: speech recognition over the telephone line.
  
• Valérie Hazan, Bo Shi:
  Individual variability in the perception of synthetic speech.
  
• Ye. K. Ludovic, V. V. Pilipenko, G. E. Tseitlin, L. I. Nagornaya, T. Terzian:
  Speech recognition system and its application for blind PC users.