Proceedings of the Workshop
Modeling Pronunciation Variation
for Automatic Speech Recognition

Rolduc, 4-6 May 1998



Edited by
Helmer Strik, Judith Kessens, Mirjam Wester
A2RT, Dept. of Language & Speech
University of Nijmegen, 1998



Below you can find details about the Proceedings of the Workshop 'Modeling pronunciation variation for automatic speech recognition'. Extra copies of the proceedings are available. The price is
- NLG 40 + mailing costs for ESCA members
- NLG 60 + mailing costs for non members

Mailing costs:
- NLG 10 for Europe
- NLG 20 for other countries

If you want to order a copy contact

Helmer Strik
Dept. of Language and Speech
P.O. Box 9103
6500 HD Nijmegen
the Netherlands

Tel.nr.: 31-24-3616104
Fax nr.: 31-24-3612907
E-mail : Strik@let.kun.nl
URL /lands.let.kun.nl/TSpublic/strik/



Contents

1
Pronunciation variants across systems, languages and speaking style
M. Adda-Decker, L. Lamel

7
Joint acoustic unit design and lexicon generation
M. Bacchiani, M. Ostendorf

13
Pronunciation modelling in the RWTH large vocabulary speech recognizer
K. Beulen, S. Ortmanns, A. Eiden, S. Martin, L. Welling, J. Overmann, H. Ney

17
Speech recognition methods for non-native pronunciation variations
P. Bonaventura, F. Gallocchio, J. Mari, G. Micca

23
In search of pronunciation rules
N. Cremelie, J.-P. Martens

29
Introducing multiple pronunciations in spanish speech recognition systems
J. Ferreiros, J. Mac¡as-Guarasa, J.M. Pardo, L. Villarrubia

35
Effects of speaking rate and word frequency on conversational pronunciations
E. Fosler-Lussier, N. Morgan

41
Automatic generation of multiple pronunciations based on neural networks and language statistics
T. Fukada, T. Yoshimura, Y. Sagisaka

47
Speaking in shorthand: a syllable-centric perspective for understanding pronunciation variation
S. Greenberg

57
An HMM-based probabilistic lexicon
H. Heine, G. Evermann, U. Jost

63
Maximum likelihood modelling of pronunciation variation
T. Holter, T. Svendsen

67
Generation and selection of pronunciation variants for a flexible word recognizer
G. Lehtinen, S. Safra

73
Derivation of the optimal phonetic transcription set for a word from its acoustic realisations
H. Mokbel, D. Jouvet

79
Context and speed dependent phonemic models for continuous speech recognition
F. Mouria-Beji

85
Detecting and correcting poor pronunciations for multiword units
H.J. Nock, S.J. Young

91
Phonological component in automatic speech recognition
G. Perennou, L. Brieussel-Pousse

97
Visualizing speech trajectories
S.D. Peters, P. Stubley

103
Pronunciation variations in emotional speech
T.S. Polzin, A.H. Waibel

109
Stochastic pronunciation modelling from hand-labelled phonetic corpora
M. Riley, W. Byrne, M. Finke, S. Khudanpur, A. Ljolje, J. McDonough, H. Nock, M. Saraclar, C. Wooters, G. Zavaliagkos

117
A surficial pronunciation model
E.S. Ristad, P.N. Yianilos

121
Variation information in pronunciation dictionaries
P. Roach, S. Arnfield

125
Modeling pronunciation variations and coarticulation with finite-state transducers in CSR
S. Safra, G. Lehtinen, K. Huber

131
Statistical modelling of pronunciation: it's not the model, it's the data
F. Schiel, A. Kipp, H.G. Tillmann

137
Modeling pronunciation variation for ASR: overview and comparison of methods
H. Strik, C. Cucchiarini

145
Improving the performance of a Dutch CSR by modeling pronunciation variation
M. Wester, J.M. Kessens, H. Strik

151
Confidence measures for evaluating pronunciation models
G. Williams, S. Renals

157
Dynamic and static improvements to lexical baseforms
R. Wiseman, S. Downey


Last updated on 15-05-1998

the workshop homepage