SLP-L3: Novel Architectures and Training Strategies for ASR |
| Session Type: Lecture |
| Time: Wednesday, May 15, 08:30 - 10:30 |
| Location: Auditorium 1 |
| Session Chairs: Kai Yu, Shanghai Jiao Tong University and Olivier Siohan, Google |
| SLP-L3.1: UNIVERSAL ACOUSTIC MODELING USING NEURAL MIXTURE MODELS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Amit Das; University of Illinois |
| Jinyu Li; Microsoft |
| Changliang Liu; Microsoft |
| Yifan Gong; Microsoft |
| SLP-L3.2: TIMESCALENET : A MULTIRESOLUTION APPROACH FOR RAW AUDIO RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Eric Bavu; Conservatoire National des Arts et Métiers |
| Aro Ramamonjy; Conservatoire National des Arts et Métiers |
| Hadrien Pujol; Conservatoire National des Arts et Métiers |
| Alexandre Garcia; Conservatoire National des Arts et Métiers |
| SLP-L3.3: ENCRYPTED SPEECH RECOGNITION USING DEEP POLYNOMIAL NETWORKS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Shixiong Zhang; Tencent AI Lab |
| Yifan Gong; Microsoft Corporation |
| Dong Yu; Tencent AI Lab |
| SLP-L3.4: LEARNING DISCRIMINATIVE FEATURES IN SEQUENCE TRAINING WITHOUT REQUIRING FRAMEWISE LABELLED DATA |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Jun Wang; Tencent |
| Dan Su; Tencent |
| Jie Chen; Tencent |
| Shulin Feng; Peking University |
| Dongpeng Ma; Tencent |
| Na Li; Tencent |
| Dong Yu; Tencent |
| SLP-L3.5: IMPROVING CTC USING STIMULATED LEARNING FOR SEQUENCE MODELING |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Jahn Heymann; Paderborn University |
| Khe Chai Sim; Google AI |
| Bo Li; Google AI |
| SLP-L3.6: DISTRIBUTED DEEP LEARNING STRATEGIES FOR AUTOMATIC SPEECH RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Wei Zhang; IBM |
| Xiaodong Cui; IBM |
| Ulrich Finkler; IBM |
| Brian Kingsbury; IBM |
| George Saon; IBM |
| David Kung; IBM |
| Michael Picheny; IBM |