ISCA Archive

ASR2000 - Automatic Speech Recognition: Challenges for the new Millenium

September 18-20, 2000
Paris, France



Bibliographic Reference

[ASR-2000] ASR2000 - Automatic Speech Recognition: Challenges for the new Millenium, ISCA Tutorial and Research Workshop (ITRW), Paris, France, September 18-20, 2000, ISCA Archive, http://www.isca-speech.org/archive_open/asr2000



Author Index and Quick Access to Abstracts

Adda   Ainsworth   Amdal   AUBERT   Bass   Béchet   Bilmes (17)   Bilmes (133)   Bippus   Boulianne   Bourlard   Boves   Burianek   Caseiro   Cettolo   Chang   Charlet   COHEN   Diorio   Dumouchel   Edmonds   Fakotakis   Federico   Fissore   Franco   Furui (160)   Furui (244)   Gao   Gauvain (47)   Gauvain (150)   Geller   Goronzy   Gotoh   Greenberg   Haag   Hagen   Hazen   Hilger   Hirsch   Isahara   Itoh   Jouvet   Kanthak   Kenny   Kienappel   Kirchhoff   Kokkinakis   Kompe   Korkmazskiy (58)   Korkmazskiy (85)   Laface   Lamel   Lee   Ljungqvist   Maekawa   Marasek   Meyer   MOHRI   Molau   de Mori   Morris   Myrvoll   Ney (40)   Ney (64)   Olsen   Padmanabhan (128)   PADMANABHAN (189)   Pearce   Peng   PEREIRA   Picheny (107)   PICHENY (189)   Polifroni   Potamitis   POVEY   Printz   Ramabhadran   Renals   Richardson   Rigoll   RILEY   Rottland   Saon   Schwenk   Seneff   Sienel   Siohan (58)   Siohan (120)   Sixtus   Soong   Stadermann   Stolcke   Stubley   Surendran   Torres   Trancoso   Varona   Wang   WOODLAND   Yang   Zhang   Zheng   Zweig  

Names written in boldface refer to first authors, in CAPITAL letters to invited keynote papers. Full papers can be accessed from the abstracts (ISCA members only). Please note that each abstract opens in a separate window.



Table of Contents and Access to Abstracts

Keynote Papers

Woodland, P. C. / Povey, D.: "Large scale discriminative training for speech recognition", 7-16.

Aubert, Xavier L.: "A brief overview of decoding techniques for large vocabulary continuous speech recognition", 91-96.

Mohri, Mehryar / Pereira, Fernando / Riley, Michael: "Weighted finite-state transducers in speech recognition", 97-106.

Padmanabhan, Mukund / Picheny, Michael: "Towards super-human speech recognition", 189-194.

Cohen, Michael H.: "Surfing the voice web: issues in the design of a voice browser", 236-238.

Acoustic Model Training

Kirchhoff, Katrin / Bilmes, Jeff A.: "Combination and joint training of acoustic classifiers for speech recognition", 17-23.

Stadermann, Jan / Rottland, Jörg / Rigoll, Gerhard: "Tied-Posteriors: A new hybrid speech recognition technology with generic capabilities and high portability", 24-28.

Decoding

Stubley, Peter: "The block-synchronous search algorithm", 29-34.

Caseiro, Diamantino / Trancoso, Isabel: "A decoder for finite-state structured search spaces", 35-39.

Kanthak, Stephan / Sixtus, Achim / Molau Sirko / Ney, Hermann: "Within-word vs. across-word decoding for online speech recognition", 40-46.

Schwenk, Holger / Gauvain, Jean-Luc: "Improved ROVER using language model information", 47-52.

Noise Robustness

Potamitis, I. / Fakotakis, Nikos / Kokkinakis, George: "Reliable ASR based on unreliable features ", 53-57.

Korkmazskiy, Filipp / Soong, Frank K. / Siohan, Olivier: "Constrained spectrum normalization for robust speech recognition in noise", 58-63.

Hilger, Florian / Ney, Hermann: "Noise level normalization and reference adaptation for robust speech recognition", 64-68.

Furui, Sadaoki / Itoh, Daisuke: "Noise adaptation of HMMs using neural networks", 160-167.

Meyer, G. F. / Edmonds, B. A. / Yang, D. / Ainsworth, William A.: "Amplitude modulation maps for robust speech recognition", 168-174.

Hagen, Astrid / Morris, Andrew / Bourlard, Hervé: "From multi-band full combination to multi-stream full combination processing in robust ASR", 175-180.

Hirsch, Hans-Günter / Pearce, David: "The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions", 181-188.

Language and Pronunciation Modeling

Varona, A. / Torres, I.: "Delimited smoothing technique over pruned and not pruned syntactic language models: perplexity and WER", 69-76.

Printz, Harry / Olsen, Peder: "Theory and practice of acoustic confusability", 77-84.

Amdal, Ingunn / Korkmazskiy, Filipp / Surendran, Arun C.: "Data-driven pronunciation modelling for non-native speakers using association strength between phones", 85-90.

Acoustic Model Adaptation

Gao, Yuqing / Ramabhadran, Bhuvana / Picheny, Michael: "New adaptation techniques for large vocabulary continuous speech recognition", 107-111.

Kenny, Patrick / Boulianne, Gilles / Dumouchel, Pierre: "Bayesian adaptation revisited", 112-119.

Siohan, Olivier / Myrvoll, Tor André / Lee, Chin-Hui: "Structural maximum a posteriori linear regression for fast HMM adaptation", 120-127.

Padmanabhan, Mukund / Saon, George / Zweig, Geoffrey: "Lattice-based unsupervised MLLR for speaker adaptation", 128-132.

Acoustic Modeling

Richardson, Matt / Bilmes, Jeff / Diorio, Chris: "Hidden-articulator Markov models for speech recognition", 133-139.

Peng, Gang / Zhang, Bo / Wang, William S-Y.: "Performance of Mandarin connected digit recognizer with word duration modeling", 140-144.

Zheng, Jing / Franco, Horacio / Stolcke, Andreas: "Rate-of-speech modeling for large vocabulary conversational speech recognition", 145-149.

Lamel, Lori / Gauvain, Jean-Luc / Adda, Gilles: "Lightly supervised acoustic model training", 150-154.

Kienappel, Anne-Katrin / Geller, Dieter / Bippus, Rolf: "Cross-language transfer of multilingual phoneme models", 155-159.

Error Analysis, Confidence Measures and Metadata

Greenberg, Steven / Chang, Shuangyu: "Linguistic dissection of switchboard-corpus automatic speech recognition systems", 195-202.

Charlet, Delphine: "Optimizing confidence measure based on HMM acoustical rescoring", 203-206.

Goronzy, Silke / Marasek, Krzysztof / Haag, Andreas / Kompe, Ralf: "Prosodically motivated features for confidence measures", 207-212.

Hazen, Timothy J. / Burianek, Theresa / Polifroni, Joseph / Seneff, Stephanie: "Recognition confidence scoring for use in speech understanding systems", 213-220.

Cettolo, Mauro / Federico, Marcello: "Model Selection Criteria for Acoustic Segmentation", 221-227.

Gotoh, Yoshihiko / Renals, Steve: "Sentence boundary detection in broadcast speech transcripts", 228-235.

New National and International Speech Projects and Future Prospects

Ljungqvist, Mats: "Human language technologies in European Community Research Programmes, current state and future perspectives", 239-240.

Bass, James D.: "Breaking the local optima paradigm: DARPA speech research initiatives in multi-modal and other technologies", 241-243.

Furui, Sadaoki / Maekawa, Kikuo / Isahara, Hitoshi: "A Japanese national project on spontaneous speech corpus and processing technology", 244-248.

Boves, Lou / Jouvet, Denis / Sienel, Juergen / Mori, Renato de / Béchet, Fréderic / Fissore, Luciano / Laface, Pietro: "ASR for automatic directory assistance: The SMADA project", 249-254.