SS-L3: Large-Scale Optimization for Signal Processing and Speech Recognition |
| Session Type: Lecture |
| Time: Wednesday, March 28, 10:30 - 12:30 |
| Location: Room B-1 |
| Session Chairs: Georg Heigold, Google, Inc., Dimitri Kanevsky, IBM T. J. Watson Research Center and Hermann Ney, RWTH Aachen University
|
| |
|
SS-L3.1: OVERVIEW OF LARGE SCALE OPTIMIZATION FOR DISCRIMINATIVE TRAINING IN SPEECH RECOGNITION
|
| Dimitri Kanevsky; IBM
|
| Georg Heigold; Google, Inc.
|
| Stephen Wright; University of Wisconsin
|
| Hermann Ney; RWTH Aachen University
|
| |
|
SS-L3.2: SECOND-ORDER METHODS FOR L1 REGULARIZED PROBLEMS IN MACHINE LEARNING
|
| Samantha Hansen; Northwestern University
|
| Jorge Nocedal; Northwestern University
|
| |
|
SS-L3.3: OPTIMIZATION IN SPEECH-CENTRIC INFORMATION PROCESSING: CRITERIA AND TECHNIQUES
|
| Xiaodong He; Microsoft Research
|
| Li Deng; Microsoft Research
|
| |
|
SS-L3.4: ROBUST INVERSION VIA SEMISTOCHASTIC DIMENSIONALITY REDUCTION
|
| Aleksandr Aravkin; University of British Columbia
|
| Michael Friedlander; University of British Columbia
|
| Tristan van Leeuwen; University of British Columbia
|
| |
|
SS-L3.5: UNSCENTED COMPRESSED SENSING
|
| Avishy Carmi; Nanyang Technological University
|
| Lyudmila Mihaylova; University of Lancaster
|
| Dimitri Kanevsky; IBM T.J. Watson Research Center
|
| |
|
SS-L3.6: FULLY BAYESIAN INFERENCE OF MULTI-MIXTURE GAUSSIAN MODEL AND ITS EVALUATION USING SPEAKER CLUSTERING
|
| Naohiro Tawara; Waseda University
|
| Tetsuji Ogawa; Waseda Institute for Advanced Study
|
| Shinji Watanabe; NTT Communication Science Laboratories
|
| Tetsunori Kobayashi; Waseda University
|
| |