SP-L7: Acoustic Modeling III |
| Session Type: Lecture |
| Time: Thursday, March 29, 16:30 - 18:30 |
| Location: Room B-1 |
| Session Chairs: Karen Livescu, Toyota Technological Institute at Chicago and Jasha Droppo, Microsoft Corporation
|
| |
|
SP-L7.1: LATENT PERCEPTUAL MAPPING WITH DATA-DRIVEN VARIABLE-LENGTH ACOUSTIC UNITS FOR TEMPLATE-BASED SPEECH RECOGNITION
|
| Shiva Sundaram; Deutsche Telekom Laboratories
|
| Jerome Bellegarda; Apple Inc.
|
| |
|
SP-L7.2: DISTRIBUTED ACOUSTIC MODELING WITH BACK-OFF N-GRAMS
|
| Ciprian Chelba; Google, Inc.
|
| Peng Xu; Google, Inc.
|
| Fernando Pereira; Google, Inc.
|
| Thomas Richardson; University of Washington
|
| |
|
SP-L7.3: N-BEST ENTROPY BASED DATA SELECTION FOR ACOUSTIC MODELING
|
| Nobuyasu Itoh; IBM Research - Tokyo
|
| Tara N. Sainath; IBM T.J. Watson Research Center
|
| Dan Ning Jiang; IBM Research - China
|
| Jie Zhou; IBM Research - China
|
| Bhuvana Ramabhadran; IBM T.J. Watson Research Center
|
| |
|
SP-L7.4: ANALYZING QUALITY OF CROWD-SOURCED SPEECH TRANSCRIPTIONS OF NOISY AUDIO FOR ACOUSTIC MODEL ADAPTATION
|
| Kartik Audhkhasi; University of Southern California
|
| Panayiotis Georgiou; University of Southern California
|
| Shrikanth Narayanan; University of Southern California
|
| |
|
SP-L7.5: CONSTRUCTING ENSEMBLES OF DISSIMILAR ACOUSTIC MODELS USING HIDDEN ATTRIBUTES OF TRAINING DATA
|
| Takashi Fukuda; IBM Research - Tokyo
|
| Ryuki Tachibana; IBM Research - Tokyo
|
| Upendra Chaudhari; IBM T.J. Watson Research Center
|
| Bhuvana Ramabhadran; IBM T.J. Watson Research Center
|
| Puming Zhan; Nuance Communications Inc.
|
| |
|
SP-L7.6: KNOWLEDGE-BASED QUADRATIC DISCRIMINANT ANALYSIS FOR PHONETIC CLASSIFICATION
|
| Heyun Huang; Radboud University Nijmegen
|
| Yang Liu; Yale University
|
| Louis Ten Bosch; Radboud University Nijmegen
|
| Bert Cranen; Radboud University Nijmegen
|
| Lou Boves; Radboud University Nijmegen
|
| |