SP-L5: Acoustic Modeling I |
| Session Type: Lecture |
| Time: Thursday, March 29, 10:30 - 12:30 |
| Location: Room B-1 |
| Session Chairs: Brian Mak, Hong Kong University of Science and Technology and Hermann Ney, RWTH Aachen University
|
| |
|
SP-L5.1: A STUDY OF DISCRIMINATIVE FEATURE EXTRACTION FOR I-VECTOR BASED ACOUSTIC SNIFFING IN IVN ACOUSTIC MODEL TRAINING
|
| Yu Zhang; Shanghai Jiao Tong University
|
| Jian Xu; University of Science and Technology of China
|
| Zhi-Jie Yan; Microsoft Research Asia
|
| Qiang Huo; Microsoft Research Asia
|
| |
|
SP-L5.2: COMPARISON AND COMBINATION OF DIFFERENT CRBE BASED MLP FEATURES FOR LVCSR
|
| Zoltán Tüske; RWTH Aachen University
|
| Ralf Schlüter; RWTH Aachen University
|
| Hermann Ney; RWTH Aachen University
|
| |
|
SP-L5.3: REVISITING RECURRENT NEURAL NETWORKS FOR ROBUST ASR
|
| Oriol Vinyals; University of California at Berkeley
|
| Suman Ravuri; University of California at Berkeley
|
| Daniel Povey; Microsoft Research
|
| |
|
SP-L5.4: A COMPARATIVE STUDY OF DISCRIMINATIVE TRAINING USING NON-UNIFORM CRITERIA FOR CROSS-LAYER ACOUSTIC MODELING
|
| Chao Weng; Georgia Institute of Technology
|
| Biing-Hwang (Fred) Juang; Georgia Institute of Technology
|
| |
|
SP-L5.5: TOWARDS SINGLE PASS DISCRIMINATIVE TRAINING FOR SPEECH RECOGNITION
|
| Roger Hsiao; Carnegie Mellon University
|
| Tanja Schultz; Carnegie Mellon University
|
| |
|
SP-L5.6: DERIVATION OF EIGENTRIPHONES BY WEIGHTED PRINCIPAL COMPONENT ANALYSIS
|
| Tom Ko; The Hong Kong University of Science and Technology
|
| Brian Mak; The Hong Kong University of Science and Technology
|
| |