practical information about the workshop
On this page you can find some practical information about the workshop
'Modeling pronunciation variation for automatic speech recognition':
- program
- list of participants
- details about the social event
program
Sunday 3 May
19:00 - 23:00 registration either near the main entrance or
in the cellar bar 'the prodigal son'
21:00 guided walking tours through Rolduc
Monday 4 May
09:30 opening session
welcome to Rolduc and the workshop
welcome address by Roger Moore
practical information
10:45 break
*** Session: cross-word variation
chair: Lori Lamel
11:15 1. Nock
Title: Detecting and correcting poor pronunciations for multiword units
Author(s): H.J. Nock & S.J. Young
11:45 2. Perennou
Title: Phonological component in automatic speech recognition
Author(s): G. Perennou & L. Brieussel-Pousse
12:15 3. Safra
Title: Modeling pronunciation variations and coarticulation with finite-state transducers in CSR
Author(s): S. Safra, G. Lehtinen & K. Huber
12:45 general discussion
13:00 lunch
*** Session: rule-based methods
chair: Jean-Pierre Martens
14:00 1. Mouria
Title: Context and speed dependent phonemic models for continuous speech recognition
Author(s): F. Mouria-Beji
14:30 2. Lehtinen
Title: Generation and selection of pronunciation variants for a flexible word recognizer
Author(s): G. Lehtinen & S. Safra
15:00 3. Ferreiros
Title: Introducing multiple pronunciations in spanish speech recognition systems
Author(s): J. Ferreiros, J. Mac!!!ias-Guarasa, J.M. Pardo & L. Villarrubia
15:30 break
16:00 4. Wester
Title: Improving the performance of a Dutch CSR by modelling pronunciation variation
Author(s): M. Wester, J.M. Kessens & H. Strik
16:30 5. Schiel
Title: Statistical modelling of pronunciation: it's not the model, it's the data
Author(s): F. Schiel, A. Kipp & H.G. Tillmann
17:00 6. Cremelie
Title: In search of pronunciation rules
Author(s): N. Cremelie & J.-P. Martens
17:30 general discussion
18:30 dinner
21:00 guided walking tours through Rolduc
drinks in the cellar bar 'the prodigal son'
Tuesday 5 May
*** Session: optimizing lexicon & acoustic models
chair: Torbjorn Svendsen
09:30 keynote: Riley
Title: Stochastic pronunciation modeling from hand-labelled phonetic corpora
Author(s): M. Riley, W. Byrne, M. Finke, S. Khudanpur, A. Ljolje, J. McDonough, H. Nock, M. Saraclar, C. Wooters, G. Zavaliagkos
10:15 2. Holter
Title: Maximum likelihood modelling of pronunciation variation
Author(s): T. Holter & T. Svendsen
10:45 break
11:15 3. Beulen
Title: Pronunciation modelling in the RWTH large vocabulary speech recognizer
Author(s): K. Beulen, S. Ortmanns, A. Eiden, S. Martin, L. Welling, J. Overmann & H. Ney
11:45 4. Ristad
Title: A surficial pronunciation model
Author(s): E.S. Ristad & P.N. Yianilos
12:15 5. Roach
Title: Variation information in pronunciation dictionaries
Author(s): P. Roach & S. Arnfield
12:45 general discussion
13:00 lunch
14:00 6. Williams
Title: Confidence measures for evaluating pronunciation models
Author(s): G. Williams & S. Renals
*** Session: overview and evaluation
chair: Torbjorn Svendsen
14:30 1. Strik
Title: Modeling pronunciation variation for ASR: evaluation and comparison of methods
Author(s): H. Strik
15:00 general discussion
15:30 break
*** Session: data-driven studies
16:00 posters of
1. Fosler
Title: Effects of speaking rate and word frequency on conversational pronunciations
Author(s): E. Fosler-Lussier & N. Morgan
2. Fukada
Title: Automatic generation of multiple pronunciations based on neural networks and language statistics
Author(s): T. Fukada, T. Yoshimura & Y. Sagisaka
3. Heine
Title: An HMM-based probabilistic lexicon
Author(s): H. Heine, G. Evermann & U. Jost
4. Mokbel
Title: Derivation of the optimal phonetic transcription set for a word from its acoustic realisations
Author(s): H. Mokbel & D. Jouvet
5. Peters
Title: Visualizing speech trajectories
Author(s): S.D. Peters & P. Stubley
6. Polzin
Title: Pronunciation variations in emotional speech
Author(s): T.S. Polzin & A.H. Waibel
7. Wiseman
Title: Dynamic and static improvements to lexical baseforms
Author(s): R. Wiseman & S. Downey
19:00 dinner
a buffet in the cellar bar 'the prodigal son'
Wednesday 6 May
*** Session: in search of better basic units
chair: Liz Shriberg
09:30 keynote: Greenberg
Title: Speaking in shorthand: a syllable-centric perspective on understanding pronunciation variation
Author(s): S. Greenberg
10:15 2. Bacchiani
Title: Joint acoustic unit design and lexicon generation
Author(s): M. Bacchiani & M. Ostendorf
10:45 break
*** Session: multilingual studies
chair: Loe Boves
11:15 1. Adda-Decker
Title: Pronunciation variants across systems, languages and speaking style
Author(s): M. Adda-Decker & L. Lamel
11:45 2. Bonaventura
Title: Speech recognition methods for non-native pronunciation variations
Author(s): P. Bonaventura, F. Gallocchio, J. Mari & G. Micca
12:15 general discussion
12:30 closing session
practical information
concluding words by Rolf Carlson
epilogue
13:00 lunch
14:00 social event
Estimated time-schedule:
- 14:00: departure from Rolduc to Maastricht
- 18:30: departure from Maastricht to Château Neercanne
- 23:00: departure from Château Neercanne to Rolduc
list of participants
Participants Affiliation Country e-mail address
Adda-Decker, Martine LIMSI France madda@limsi.fr
Andersen, Ove Aalborg University Denmark oa@cpk.auc.dk
Bacchiani, Michiel Boston University USA bacchian@raven.bu.edu
Batliner, Anton Erlangen University Germany batliner@informatik.uni-erlangen.de
Beulen, Klaus RWTH Aachen Germany beulen@informatik.rwth-aachen.de
Bosch, Louis ten Lernout&Hauspie Belgium tenbosch@baard.lhs.be
Boves, Loe A2RT, University of Nijmegen Netherlands boves@let.kun.nl
Brieussel-Pousse,Laure University of Toulouse/IRIT France laure.brieussel@irin.univ-nantes.fr
Browning, Sue DERA Speech Research Unit UK srb@signal.dera.gov.uk
Carlson, Rolf Dept. Speech, Music & Hearing Sweden rolf@speech.kth.se
Cerrato, Loredana Fondazione Ugo Bordoni Italy loredana@fub.it
Cohen, Paul IBM Corporation USA cohen@watson.ibm.com
Cremelie, Nick ELIS, RUG Belgium cremelie@elis.rug.ac.be
Cucchiarini, Catia A2RT, University of Nijmegen Netherlands catia@let.kun.nl
D'hoore, Bart Lernout&Hauspie Belgium bart.dhoore@lhs.be
Deroo, Olivier Faculte Polytechnique de Mons Belgium deroo@tcts.fpms.ac.be
Drenth, Erwin KPN Research Netherlands E.W.Drenth@research.kpn.com
Elenius, Kjell KTH, Speech, Music & Hearing Sweden kjell@speech.kth.se
Espain, Carlos DEEC Portugal espain@garfield.fe.up.pt
Ferreiros, Javier GTH-IEL-UPM Spain jfl@die.upm.es
Finke, Michael Carnegie Mellon University USA finkem@cs.cmu.edu
Fontinea, Evita ILSP, National Techn. Univ. of Athens Greece evita@ilsp.gr
Fosler-Lussier, Eric Intern. Computer Science Inst. USA fosler@icsi.berkeley.edu
Fukada, Toshiaki Carnegie Mellon University USA tfukada@cs.cmu.edu
Greenberg, Steven Intern. Computer Science Inst. USA steveng@icsi.Berkeley.EDU
Hariharan, Ramalingam Nokia Research Center Finland ramalingam.hariharan@research.nokia.com
Heuft, Barbara Philips Speech Processing Germany heuft@acn.be.philips.com
Hoegberg, Jesper Dept. Speech, Music & Hearing Sweden jesper@speech.kth.se
Johansen, Finn Tore Telenor R&D Norway finn.johansen@fou.telenor.no
Jost, Uwe Cannon Research UK uwe@cre.canon.co.uk
Kessens, Judith A2RT, University of Nijmegen Netherlands kessens@let.kun.nl
Khudanpur, Sanjeev P. Johns Hopkins University USA khudanpur@jhu.edu
Kiraz, George Bell Labs USA gkiraz@research.bell-labs.com
Lamel, Lori LIMSI France lamel@limsi.fr
Lehtinen, Gunnar Computer, Engineering & Networks Lab. Switzerland lehtinen@tik.ee.ethz.ch
Lynch, Thomas Lernout&Hauspie USA tlynch@lhs.com
Martens, Jean-Pierre ELIS, RUG Belgium martens@elis.rug.ac.be
Micca, Giorgio CSELT Italy giorgio.micca@cselt.it
Mokbel, Houda France Telecom France houda.mokbel@cnet.francetelecom.fr
Molau, Sirko RWTH Aachen Germany molau@informatik.rwth-aachen.de
Moore, Roger DERA, Speech Research Unit UK moore@signal.dra.hmg.gb
Mouria-Beji, F. AIG, Tunis Tunisia maddouri@ensi.rnrt.tn
Nock, Harriet Johns Hopkins University USA hjn11@mail.clsp.jhu.edu
Ostendorf, Mari Boston University USA mo@raven.bu.edu
Pera, Vitor DEEC Portugal pera@alf.fe.up.pt
Perennou, Guy Universite Paul Sabatier France perennou@irit.fr
Peters, Douglas Nortel Canada peters@nortel.ca
Pols, Louis Institute of Phonetic Sciences Netherlands pols@fon.let.uva.nl
Polzin, Thomas Carnegie Mellon University USA tpolzin@cs.cmu.edu
Ravera, Franco CSELT Italy franco.ravera@cselt.it
Richards, Hywel Dragon Systems UK Ltd UK Hywell@dragonsys.com
Riley, Michael AT&T Labs Research USA riley@research.att.com
Ringland, Simon BT Laboratories UK spar@saltfarm.bt.co.uk
Roach, Peter University of Reading UK p.j.roach@reading.ac.uk
Safra, Schamai Computer Engineering & Networks Lab. Switzerland safra@tik.ee.ethz.ch
Sagisaka,Yoshinori ATR Interpr.Telecommunications Japan sagisaka@itl.atr.co.jp
Schiel, Florian University of Munich Germany schiel@phonetik.uni-muenchen.de
Schlueter, Ralf RWTH Aachen Germany schlueter@informatik.rwth-aachen.de
Shammass, Shaunie NSC (Natural Speech Communication) Ltd. Israel shaunie@nsc.co.il
Shriberg, Elizabeth SRI International USA ees@speech.sri.com
Smaili, Kamel CRIN/INRIA France smaili@loria.fr
Strik, Helmer A2RT, University of Nijmegen Netherlands strik@let.kun.nl
Svendsen,Torbjorn Dept. of Telecommunications, NTNU Norway torbjorn@tele.ntnu.no
Vicsi, Klara University of Budapest Hungary vicsi@sparc.core.hu
Wester, Mirjam A2RT, University of Nijmegen Netherlands wester@let.kun.nl
Wet, Febe de University of Pretoria/A2RT South Africa F.de.Wet@let.kun.nl
Wilcox, Patricia Philips Speech Processing Germany wilcox@pfa.research.philips.com
Williams, Gethin Int. Computer Science Inst. USA williams@icsi.berkeley.edu
Wiseman, Richard BT Laboratories UK Richard.Wiseman@bt.com
Wolff, Matthias Dresden Univ. of Technology Germany wolff@eakss1.et.tu-dresden.de
Yianilos, Peter NEC Research Institute USA pny@research.nj.nec.com
Yvon, Francois ENST France yvon@inf.enst.fr
Social event
Maastricht is a well-known European
town since an important European
summit took place there. Furthermore, and more important, Maastricht is a
very beautiful town. That is whe we will visit Maastricht on Wednesday
afternoon. We will organize a guided walking tour through Maastricht.
If the weather is not good enough we will probably visit the Bonnefanten
museum.
In the evening we will have dinner at
Château Neercanne which is one of the
most beautifully located and famous restaurants of the Netherlands.
During the European summit mentioned above, the Queen of the Netherlands
invited the European leaders to dinner at this Château.
Busses will take you from Rolduc to Maastricht, then to Château
Neercanne, and finally back to Rolduc.
Estimated time-schedule:
- 14:00: departure from Rolduc to Maastricht
- 18:30: departure from Maastricht to Château Neercanne
- 23:00: departure from Château Neercanne to Rolduc
Last updated on 17-06-1998
the workshop homepage