SPE-46.2
CONTINUOUS STREAMING MULTI-TALKER ASR WITH DUAL-PATH TRANSDUCERS
Desh Raj, Johns Hopkins University, United States of America; Liang Lu, Zhuo Chen, Yashesh Gaur, Jinyu Li, Microsoft Corp., United States of America
Session:
Multi Speaker and Multi-Channel Speech Recognition and Processing
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Tue, 10 May, 23:00 - 23:45 China Time (UTC +8)
Tue, 10 May, 15:00 - 15:45 UTC
Tue, 10 May, 15:00 - 15:45 UTC
Session Chair:
Shinji Watanabe, CMU
Session SPE-46
SPE-46.1: Endpoint Detection for Streaming End-to-End Multi-talker ASR
Liang Lu, Otter.ai, United States of America; Jinyu Li, Yifan Gong, Microsoft, USA, United States of America
SPE-46.2: CONTINUOUS STREAMING MULTI-TALKER ASR WITH DUAL-PATH TRANSDUCERS
Desh Raj, Johns Hopkins University, United States of America; Liang Lu, Zhuo Chen, Yashesh Gaur, Jinyu Li, Microsoft Corp., United States of America
SPE-46.3: EXTENDED GRAPH TEMPORAL CLASSIFICATION FOR MULTI-SPEAKER END-TO-END ASR
Xuankai Chang, Shinji Watanabe, Carnegie Mellon University, United States of America; Niko Moritz, Facebook AI, United Kingdom of Great Britain and Northern Ireland; Takaaki Hori, Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States of America
SPE-46.4: ADA-VAD: UNPAIRED ADVERSARIAL DOMAIN ADAPTATION FOR NOISE-ROBUST VOICE ACTIVITY DETECTION
Taesoo Kim, Jong Hwan Ko, Sungkyunkwan university, Korea, Republic of; Jiho Chang, Korea Research Institute of Standards and Science, Korea, Republic of
SPE-46.5: MULTI-CHANNEL END-TO-END NEURAL DIARIZATION WITH DISTRIBUTED MICROPHONES
Shota Horiguchi, Yuki Takashima, Yohei Kawaguchi, Hitachi, Ltd., Japan; Paola Garcia, Johns Hopkins University, United States of America; Shinji Watanabe, Carnegie Mellon University, United States of America
SPE-46.6: MULTI-CHANNEL SPEAKER DIARIZATION USING SPATIAL FEATURES FOR MEETINGS
Naijun Zheng, XunYing Liu, Helen Meng, The Chinese University of Hong Kong, Hong Kong; Na Li, Jianwei Yu, Chao Weng, Dan Su, Tencent AI Lab, Hong Kong