SLP-L12: Discriminative Training |
| Session Type: Lecture |
| Time: Friday, May 19, 14:00 - 16:00 |
| Location: Auditorium St Exupery |
| Chair: Michiel Bacchiani, Google, Inc. |
| SLP-L12.1: LARGE MARGIN GAUSSIAN MIXTURE MODELING FOR PHONETIC CLASSIFICATION AND RECOGNITION |
| Fei Sha, Lawrence Saul, University of Pennsylvania, United States |
| SLP-L12.2: RECENT IMPROVEMENT ON MAXIMUM RELATIVE MARGIN ESTIMATION OF HMMS FOR SPEECH RECOGNITION |
| Chaojun Liu, Panasonic R&D Company of America, United States; Hui Jiang, York University, Canada; Luca Rigazio, Panasonic R&D Company of America, United States |
| SLP-L12.3: TRAINING ALGORITHMS FOR HIDDEN CONDITIONAL RANDOM FIELDS |
| Milind Mahajan, Asela Gunawardana, Alex Acero, Microsoft Research, United States |
| SLP-L12.4: MAXIMUM CONDITIONAL MUTUAL INFORMATION WEIGHTED SCORING FOR SPEECH RECOGNITION |
| Mohamed Omar, Ganesh Ramaswamy, IBM T. J. Watson Research Center, United States |
| SLP-L12.5: JOINT DISCRIMINITIVE FRONT END AND BACK END TRAINING FOR IMPROVED SPEECH RECOGNITION ACCURACY |
| Jasha Droppo, Alex Acero, Microsoft Research, United States |
| SLP-L12.6: DISCRIMINANT INITIALIZATION FOR FACTOR ANALYZED HMM TRAINING |
| Fabrice Lefevre, Jean-Luc Gauvain, LIMSI-CNRS, France |
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012