SP-L8: Acoustic Modeling: New Search Features and Supervised Training |
| Session Type: Lecture |
| Time: Friday, May 21, 09:30 - 11:30 |
| Location: Grand Salon |
| Chair: Renato de Mori, University of Avignon |
| SP-L8.1: EFFECTS OF TRANSCRIPTION ERRORS ON SUPERVISED LEARNING IN SPEECH RECOGNITION |
| Ram Sundaram; Conversay |
| Joseph Picone; Mississippi State University |
| SP-L8.2: COMBINATION OF HIDDEN MARKOV MODELS WITH DYNAMIC TIME WARPING FOR SPEECH RECOGNITION |
| Scott Axelrod; IBM T. J. Watson Research Center |
| Benoît Maison; IBM T. J. Watson Research Center |
| SP-L8.3: JOINT DECODING FOR PHONEME-GRAPHEME CONTINUOUS SPEECH RECOGNITION |
| Mathew Magimai.-Doss; Dalle Molle Institute for Artificial Intelligence |
| Samy Bengio; Dalle Molle Institute for Artificial Intelligence |
| Hervé Bourlard; Dalle Molle Institute for Artificial Intelligence |
| SP-L8.4: A LOCALLY WEIGHTED DISTANCE MEASURE FOR EXAMPLE BASED SPEECH RECOGNITION |
| Mathias De Wachter; Katholieke Universiteit Leuven |
| Kris Demuynck; Katholieke Universiteit Leuven |
| Patrick Wambacq; Katholieke Universiteit Leuven |
| Dirk Van Compernolle; Katholieke Universiteit Leuven |
| SP-L8.5: LIGHT SUPERVISION IN ACOUSTIC MODEL TRAINING |
| Long Nguyen; BBN Technologies |
| Bing Xiang; BBN Technologies |
| SP-L8.6: LIGHTLY SUPERVISED ACOUSTIC MODEL TRAINING USING CONSENSUS NETWORKS |
| Langzhou Chen; LIMSI-CNRS |
| Lori Lamel; LIMSI-CNRS |
| Jean-Luc Gauvain; LIMSI-CNRS |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops