default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDEUROSPEECH 1997: Rhodes, Greece
- George Kokkinakis, Nikos Fakotakis, Evangelos Dermatas:
Fifth European Conference on Speech Communication and Technology, EUROSPEECH 1997, Rhodes, Greece, September 22-25, 1997. ISCA 1997
Keynotes
- Mario Rossi:
Is syntactic structure prosodically recoverable? - Victor W. Zue:
Conversational interfaces: advances and challenges. - Jan P. H. van Santen:
Prosodic modelling in text-to-speech synthesis. - Jean-Claude Junqua:
Impact of the unknown communication channel on automatic speech recognition: a review KN-29. - Jerome R. Bellegarda:
Statistical techniques for robust ASR: review and perspectives. - Richard P. Lippmann, Beth A. Carlson:
Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering and noise KN-37.
Acoustic Modelling
- Stéphane Dupont, Hervé Bourlard:
Using multiple time scales in a multi-stream speech recognition system. 3-6 - Yumi Wakita, Harald Singer, Yoshinori Sagisaka:
Speech recognition using HMM-state confusion characteristics. 7-10 - Cristina Chesta, Pietro Laface, Franco Ravera:
Bottom-up and top-down state clustering for robust acoustic modeling. 11-14 - Ralf Schlüter, Wolfgang Macherey, Stephan Kanthak, Hermann Ney, Lutz Welling:
Comparison of optimization methods for discriminative training criteria. 15-18 - Clark Z. Lee, Douglas D. O'Shaughnessy:
Clustering beyond phoneme contexts for speech recognition. 19-22 - Rathinavelu Chengalvarayan:
Influence of outliers in training the parametric trajectory models for speech recognition. 23-26 - Trym Holter, Torbjørn Svendsen:
Incorporating linguistic knowledge and automatic baseform generation in acoustic subword unit based speech recognition. 1159-1162 - Peter Beyerlein, Meinhard Ullrich, Patricia Wilcox:
Modelling and decoding of crossword context dependent phones in the Philips large vocabulary continuous speech recognition system. 1163-1166 - Philip Hanna, Ji Ming, Peter O'Boyle, Francis Jack Smith:
Modelling inter-frame dependence with preceeding and succeeding frames. 1167-1170 - Rhys James Jones, Simon Downey, John S. D. Mason:
Continuous speech recognition using syllables. 1171-1174 - Daniel Willett, Gerhard Rigoll:
A new approach to generalized mixture tying for continuous HMM-based speech recognition. 1175-1178 - Klaus Beulen, Elmar Bransch, Hermann Ney:
State tying for context dependent phoneme models. 1179-1182 - Jacques Duchateau, Kris Demuynck, Dirk Van Compernolle:
A novel node splitting criterion in decision tree construction for semi-continuous HMMs. 1183-1186 - Mats Blomberg:
Creating unseen triphones by phone concatenation in the spectral, cepstral and formant domains. 1187-1190 - Thilo Pfau, Manfred Beham, Wolfgang Reichl, Günther Ruske:
Creating large subword units for speech recognition. 1191-1194 - Jacob Goldberger, David Burshtein, Horacio Franco:
Segmental modeling using a continuous mixture of non-parametric models. 1195-1198 - Jane W. Chang, James R. Glass:
Segmentation and modeling in segment-based recognition. 1199-1202 - Alfred Hauenstein:
Using syllables in a hybrid HMM-ANN recognition system. 1203-1206 - Ramalingam Hariharan, Juha Häkkinen, Kari Laurila, Janne Suontausta:
Noise robust segment-based word recognition using vector quantisation. 1207-1210 - Luis Javier Rodríguez, M. Inés Torres:
Viterbi based splitting of phoneme HMM's. 1211-1214 - José B. Mariño, Albino Nogueiras, Antonio Bonafonte:
The demiphone: an efficient subword unit for continuous speech recognition. 1215-1218 - Hiroaki Kojima, Kazuyo Tanaka:
Organizing phone models based on piecewise linear segment lattices of speech samples. 1219-1222 - Ivica Rogina:
Automatic architecture design by likelihood-based context clustering with crossvalidation. 1223-1226 - Sam T. Roweis, Abeer Alwan:
Towards articulatory speech recognition: learning smooth maps to recover articulator information. 1227-1230 - Anastasios Tsopanoglou, Nikos Fakotakis:
Selection of the most effective set of subword units for an HMM-based speech recognition system. 1231-1234 - Christophe Cerisara, Jean Paul Haton, Jean-François Mari, Dominique Fohr:
Multi-band continuous speech recognition. 1235-1238 - Nabil N. Bitar, Carol Y. Espy-Wilson:
The design of acoustic parameters for speaker-independent speech recognition. 1239-1242
Dynamic Articulatory Measurements
- Laurence Candille, Henri Meloni:
Adaptation of natural articulatory movements to the control of the command parameters of a production model. 27-30 - Maureen L. Stone, Andrew J. Lundberg, Edward P. Davis, Rao P. Gullapalli, Moriel NessAiver:
Three-dimensional coarticulatory strategies of tongue movement. 31-34 - Nathalie Parlangeau, Régine André-Obrecht:
From laryngographic and acoustic signals to voicing gestures. 35-38 - Erkki Vilkman, Raija Takalo, Taisto Maatta, Anne-Maria Laukkanen, Jaana Nummenranta, Tero Lipponen:
Ultrasonographic measurement of cricothyroid space in speech. 39-42 - Didier Demolin, Martine George, Véronique Lecuit, Thierry Metens, Alain Soquet, H. Raeymaekers:
Coarticulation and articulatory compensations studied by dynamic MRI. 43-46 - Pierre Badin, Enrico Baricchi, Anne Vilain:
Determining tongue articulation: from discrete fleshpoints to continuous shadow. 47-50
Language Identification
- Marc A. Zissman:
Predicting, diagnosing and improving automatic language identification performance. 51-54 - Cristobal Corredor-Ardoy, Jean-Luc Gauvain, Martine Adda-Decker, Lori Lamel:
Language identification with language-independent acoustic models. 55-58 - Eluned S. Parris, Harvey Lloyd-Thomas, Michael J. Carey, Jerry H. Wright:
Bayesian methods for language verification. 59-62 - HingKeung Kwan, Keikichi Hirose:
Use of recurrent network for unknown language rejection in language identification system. 63-66 - Ove Andersen, Paul Dalsgaard:
Language-identification based on cross-language acoustic models and optimised information combination. 67-70 - Jirí Navrátil, Werner Zühlke:
Phonetic-context mapping in language identification. 71-74
Neural Networks for Speech and Language Processing
- Mazin Rahim, Yoshua Bengio, Yann LeCun:
Discriminative feature and model design for automatic speech recognition. 75-78 - Jörg Rottland, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll:
Large vocabulary speech recognition with context dependent MMI-connectionist / HMM systems using the WSJ database. 79-82 - Thierry Moudenc, Guy Mercier:
Automatic selection of segmental acoustic parameters by means of neural-fuzzy networks for reordering the n-best HMM hypotheses. 83-86 - Mikko Kurimo:
Comparison results for segmental training algorithms for mixture density HMMs. 87-90 - M. Asunción Castaño, Francisco Casacuberta:
A connectionist approach to machine translation. 91-94 - Nicolas Pican, Jean-François Mari, Dominique Fohr:
Continuous speech recognition using a context sensitive ANN and HMM2s. 95-98
Training Techniques; Efficient Decoding in ASR
- Koichi Shinoda, Takao Watanabe:
Acoustic modeling based on the MDL principle for speech recognition. 99-102 - Piyush Modi, Mazin Rahim:
Discriminative utterance verification using multiple confidence measures. 103-106 - Enrico Bocchieri, Brian Mak:
Subspace distribution clustering for continuous observation density hidden Markov models. 107-110 - Harriet J. Nock, Mark J. F. Gales, Steve J. Young:
A comparative study of methods for phonetic decision-tree state clustering. 111-114 - Alfred Kaltenmeier, Jürgen Franke:
Comparing Gaussian and polynomial classification in SCHMM-based recognition systems. 115-118 - Alexandre Girardi, Harald Singer, Kiyohiro Shikano, Satoshi Nakamura:
Maximum likelihood successive state splitting algorithm for tied-mixture HMNET. 119-122 - Erik McDermott, Shigeru Katagiri:
String-level MCE for continuous phoneme recognition. 123-126 - Zeév Rivlin, Ananth Sankar, Harry Bratt:
HMM state clustering across allophone class boundaries. 127-130 - Mehryar Mohri, Michael Riley:
Weighted determinization and minimization for large vocabulary speech recognition. 131-134 - Steven J. Phillips, Anne Rogers:
Parallel speech recognition. 135-138 - Stefan Ortmanns, Thorsten Firzlaff, Hermann Ney:
Fast likelihood computation methods for continuous mixture densities in large vocabulary speech recognition. 139-142 - Kris Demuynck, Jacques Duchateau, Dirk Van Compernolle:
A static lexicon network representation for cross-word context dependent phones. 143-146 - Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo, Pieter de Souza:
Decision-tree based quantization of the feature space of a speech recognizer. 147-150 - Mosur Ravishankar, Roberto Bisiani, Eric H. Thayer:
Sub-vector clustering to improve memory and speed performance of acoustic likelihood computation. 151-154 - Simon Hovell:
The incorporation of path merging in a dynamic network recogniser. 155-158 - Miroslav Novak:
Improvement on connected digits recognition using duration constraints in the asynchronous decoding scheme. 159-162 - Andreas Stolcke, Yochai Konig, Mitchel Weintraub:
Explicit word error minimization in n-best list rescoring. 163-166 - Long Nguyen, Richard M. Schwartz:
Efficient 2-pass n-best decoder. 167-170 - Tomohiro Iwasaki, Yoshiharu Abe:
A memory management method for a large word network. 171-174
Prosody
- Antonio Romano:
Persistence of prosodic features between dialectal and standard Italian utterances in six sub-varieties of a region of southern Italy (salento): first assessments of the results of a recognition test and an instrumental analysis. 175-178 - Halewijn Vereecken, Annemie Vorstermans, Jean-Pierre Martens, Bert Van Coile:
Improving the phonetic annotation by means of prosodic phrasing. 179-182 - Cecilia Odé:
A descriptive study of prosodic phenomena in Mpur (west Papuan Phylum). 183-186 - Hansjörg Mixdorff, Hiroya Fujisaki:
Automated quantitative analysis of F0 contours of utterances from a German ToBI-labeled speech database. 187-190 - Stéphanie de Tournemire:
Identification and automatic generation of prosodic contours for a text-to-speech synthesis system in French. 191-194 - Jinfu Ni, Ren-Hua Wang, Keikichi Hirose:
Quantitative analysis and formulation of tone concatenation in Chinese F0 contours. 195-198 - Christel Brindöpke, Arno Pahde, Franz Kummert, Gerhard Sagerer:
An environment for the labelling and testing of melodic aspects of speech. 199-202 - David Casacuberta, Lourdes Aguilar, Rafael Marín:
PROPAUSE: a syntactico-prosodic system designed to assign pauses. 203-206 - Volker Warnke, Ralf Kompe, Heinrich Niemann, Elmar Nöth:
Integrated dialog act segmentation and classification using prosodic features and language models. 207-210 - Monique E. van Donzel, Florien J. Koopmans-van Beinum:
Evaluation of prosodic characteristics in retold stories in Dutch by means of semantic scales. 211-214 - Gösta Bruce, Marcus Filipsson, Johan Frid, Björn Granström, Kjell Gustafson, Merle Horne, David House:
Text-to-intonation in spontaneous Swedish. 215-218 - Yann Morlec, Gérard Bailly, Véronique Aubergé:
Synthesising attitudes with global rhythmic and intonation contours. 219-222 - Dafydd Gibbon, Claudia Sassen:
Prosody-particle pairs as discourse control signs. 223-226 - Anja Elsner:
Focus detection with additional information of phrase boundaries and sentence mode. 227-230 - Laura Bosch, Núria Sebastián-Gallés:
The role of prosody in infants' native-language discrimination abilities: the case of two phonologically close languages. 231-234 - Eugene H. Buder, Anders Eriksson:
Prosodic cycles and interpersonal synchrony in American English and Swedish. 235-238 - Eva Strangert:
Relating prosody to syntax: boundary signalling in Swedish. 239-242 - Mitsuru Nakai, Hiroshi Shimodaira:
On representation of fundamental frequency of speech for prosody analysis using reliability function. 243-246 - Seong-Hwan Kim, Jin-Young Kim:
Efficient method of establishing words tone dictionary for Korean TTS system. 247-250 - Mariapaola D'Imperio, David House:
Perception of questions and statements in Neapolitan Italian. 251-254
Keyword and Topic Spotting
- Qiguang Lin, David M. Lubensky, Michael Picheny, P. Srinivasa Rao:
Key-phrase spotting using an integrated language model of n-grams and finite-state grammar. 255-258 - Jochen Junkawitsch, Günther Ruske, Harald Höge:
Efficient methods for detecting keywords in continuous speech. 259-262 - Raymond Lau, Stephanie Seneff:
Providing sublexical constraints for word spotting within the ANGIE framework. 263-266 - Katarina Bartkova, Denis Jouvet:
Usefulness of phonetic parameters in a rejection procedure of an HMM-based speech recognition system. 267-270 - Yoichi Yamashita, Riichiro Mizoguchi:
Keyword spotting using F0 contour matching. 271-274 - Elmar Nöth, Stefan Harbeck, Heinrich Niemann, Volker Warnke:
A frame and segment based approach for topic spotting. 275-278
Robustness in Recognition and Signal Processing
- Kuldip K. Paliwal, Yoshinori Sagisaka:
Cyclic autocorrelation-based linear prediction analysis of speech. 279-282 - Ilija Zeljkovic, Shrikanth S. Narayanan:
Novel filler acoustic models for connected digit recognition. 283-286 - Makoto Shozakai, Satoshi Nakamura, Kiyohiro Shikano:
A non-iterative model-adaptive e-CMN/PMC approach for speech recognition in car environments. 287-290 - Ángel de la Torre, Antonio M. Peinado, Antonio J. Rubio, Pedro García-Teodoro:
Discriminative feature extraction for speech recognition in noise. 291-294 - Michael K. Brendborg, Børge Lindberg:
Noise robust recognition using feature selective modeling. 295-298 - Victor Abrash:
Mixture input transformations for adaptation of hybrid connectionist speech recognizers. 299-302 - Tai-Hwei Hwang, Lee-Min Lee, Hsiao-Chuan Wang:
Adaptation of time differentiated cepstrum for noisy speech recognition. 1075-1078 - Noboru Kanedera, Takayuki Arai, Hynek Hermansky, Misha Pavel:
On the importance of various modulation frequencies for speech recognition. 1079-1082 - Wei-Tyng Hong, Sin-Horng Chen:
A robust RNN-based pre-classification for noisy Mandarin speech recognition. 1083-1086 - Mazin Rahim:
A parallel environment model (PEM) for speech recognition and adaptation. 1087-1090 - Volker Schless, Fritz Class:
Adaptive model combination for robust speech recognition in car environments. 1091-1094 - Stefaan Van Gerven, Fei Xie:
A comparative study of speech detection methods. 1095-1098 - Nikos Doukas, Patrick A. Naylor, Tania Stathaki:
Voice activity detection using source separation techniques. 1099-1102 - Tomohiko Taniguchi, Shoji Kajita, Kazuya Takeda, Fumitada Itakura:
Voice activity detection using source separation techniques. 1103-1106 - Carlos Avendaño, Sangita Tibrewala, Hynek Hermansky:
Multiresolution channel normalization for ASR in reverberant environments. 1107-1110 - Rafael Martínez, Agustín Álvarez Marquina, Pedro Gómez Vilda, Mercedes Pérez, Victor Nieto Lluis, Victoria Rodellar:
A speech pre-processing technique for end-point detection in highly non-stationary environments. 1111-1114 - Laura Docío Fernández, Carmen García-Mateo:
Application of several channel and noise compensation techiques for robust speaker recognition. 1115-1118 - Hany Agaiby, Thomas J. Moir:
Knowing the wheat from the weeds in noisy speech. 1119-1122 - Do Yeong Kim, Nam Soo Kim, Chong Kwan Un:
Model-based approach for robust speech recognition in noisy environements with multiple noise sources. 1123-1126 - Y. C. Chu, Charlie Jie, Vincent Tung, Ben Lin, Richard Lee:
Normalization of speaker variability by spectrum warping for robust speech recognition. 1127-1130 - Stéphane H. Maes
:
LPC poles tracker for music/speech/noise segmentation and music cancellation. 1131-1134 - Doh-Suk Kim, Jae-Hoon Jeong, Soo-Young Lee, Rhee Man Kil:
Comparative evaluations of several front-ends for robust speech recognition. 1135-1138 - Evandro B. Gouvêa, Richard M. Stern:
Speaker normalization through formant-based warping of the frequency scale. 1139-1142 - Martin Westphal:
The use of cepstral means in conversational speech recognition. 1143-1146 - Juan M. Huerta, Richard M. Stern:
Compensation for environmental and speaker variability by normalization of pole locations. 1147-1150 - Jean-Baptiste Puel, Régine André-Obrecht:
Cellular phone speech recognition: noise compensation vs. robust architectures. 1151-1154 - Tung-Hui Chiang:
Speech recognition in noise using on-line HMM adaptation. 1155-1158
Modelling of Prosody
- Christos Malliopoulos, George K. Mikros:
Metrical representations of demarcation and constituency in noun phrases. 303-306