SLP-P17: Robust Speech Recognition |
| Session Type: Poster |
| Time: Thursday, May 16, 18:00 - 20:00 |
| Location: Poster Area A, Ground Floor |
| Session Chair: Gregory Sell, The Johns Hopkins University |
| SLP-P17.1: ANALYZING UNCERTAINTIES IN SPEECH RECOGNITION USING DROPOUT |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Apoorv Vyas; Idiap Research Institute & École Polytechnique Fédérale de Lausanne |
| Pranay Dighe; Idiap Research Institute & École Polytechnique Fédérale de Lausanne |
| Sibo Tong; Idiap Research Institute & École Polytechnique Fédérale de Lausanne |
| Hervé Bourlard; Idiap Research Institute & École Polytechnique Fédérale de Lausanne |
| SLP-P17.2: PARAMETRIC CEPSTRAL MEAN NORMALIZATION FOR ROBUST SPEECH RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Ozlem Kalinli; Apple Inc. |
| Gautam Bhattacharya; McGill University |
| Chao Weng; Tencent AI Lab |
| SLP-P17.3: ATTENTIVE ADVERSARIAL LEARNING FOR DOMAIN-INVARIANT TRAINING |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Zhong Meng; Microsoft Corporation |
| Jinyu Li; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SLP-P17.4: JOINT TRAINING OF COMPLEX RATIO MASK BASED BEAMFORMER AND ACOUSTIC MODEL FOR NOISE ROBUST ASR |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Yong Xu; Tencent AI Lab |
| Chao Weng; Tencent AI Lab |
| Like Hui; The Ohio State University |
| Jianming Liu; Tencent AI Lab |
| Meng Yu; Tencent AI Lab |
| Dan Su; Tencent AI Lab |
| Dong Yu; Tencent AI Lab |
| SLP-P17.5: REINFORCEMENT LEARNING BASED SPEECH ENHANCEMENT FOR ROBUST SPEECH RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Yih-Liang Shen; National Chiao Tung University |
| Chao-Yuan Huang; National Chiao Tung University |
| Syu-Siang Wang; Ministry of Science and Technology |
| Yu Tsao; Academia Sinica |
| Hsin-Min Wang; Academia Sinica |
| Tai-Shih Chi; National Chiao Tung University |
| SLP-P17.6: BI-DIRECTIONAL LATTICE RECURRENT NEURAL NETWORKS FOR CONFIDENCE ESTIMATION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Qiujia Li; University of Cambridge |
| Preben Ness; University of Cambridge |
| Anton Ragni; University of Cambridge |
| Mark Gales; University of Cambridge |
| SLP-P17.7: AUC OPTIMIZATION FOR DEEP LEARNING BASED VOICE ACTIVITY DETECTION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Zi-Chen Fan; Northwestern Polytechnical University |
| Zhongxin Bai; Northwestern Polytechnical University |
| Xiao-Lei Zhang; Northwestern Polytechnical University |
| Susanto Rahardja; Northwestern Polytechnical University |
| Jingdong Chen; Northwestern Polytechnical University |
| SLP-P17.8: SPEAKER AGNOSTIC FOREGROUND SPEECH DETECTION FROM AUDIO RECORDINGS IN WORKPLACE SETTINGS FROM WEARABLE RECORDERS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Amrutha Nadarajan; Signal Analysis and Interpretation Laboratory |
| Krishna Somandepalli; Signal Analysis and Interpretation Laboratory |
| Shrikanth Narayanan; Signal Analysis and Interpretation Laboratory |
| SLP-P17.9: SPEECH AUGMENTATION USING WAVENET IN SPEECH RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Jisung Wang; VUNO |
| Sangki Kim; VUNO |
| Yeha Lee; VUNO |
| SLP-P17.10: ROBUST RECOGNITION OF REVERBERANT AND NOISY SPEECH USING COHERENCE-BASED PROCESSING |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Anjali Menon; Carnegie Mellon University |
| Chanwoo Kim; Samsing Research |
| Richard Stern; Carnegie Mellon University |
| SLP-P17.11: CYCLEGAN BANDWIDTH EXTENSION ACOUSTIC MODELING FOR AUTOMATIC SPEECH RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| David Haws; IBM |
| Xiaodong Cui; IBM |
| SLP-P17.12: VOICE ACTIVITY DETECTION USING AN ADAPTIVE CONTEXT ATTENTION MODEL |
| Juntae Kim; Korea Advanced Institute of Science and Technology |