SPE-17.3
TPARN: Triple-path attentive recurrent network for time-domain multichannel speech enhancement
Ashutosh Pandey, DeLiang Wang, The Ohio State University, United States of America; Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia, Facebook Reality Labs Research, United States of America
Session:
Speech Enhancement: Multi-channel
Track:
Speech and Language Processing
Location:
Gather Area B
Presentation Time:
Mon, 9 May, 20:00 - 20:45 China Time (UTC +8)
Mon, 9 May, 12:00 - 12:45 UTC
Mon, 9 May, 12:00 - 12:45 UTC
Session Co-Chairs:
Zhuo Chen, Microsoft and Ivan Kukanov, Institute for Infocomm Research, A*STAR
Session SPE-17
SPE-17.1: Embedding and Beamforming: All-neural Causal Beamformer for Multichannel Speech Enhancement
Andong Li, Wenzhe Liu, Chengshi Zheng, Xiaodong Li, Institute of Acoustics, Chinese Academy of Sciences, China
SPE-17.2: IMPROVING DUAL-MICROPHONE SPEECH ENHANCEMENT BY LEARNING CROSS-CHANNEL FEATURES WITH MULTI-HEAD ATTENTION
Xinmeng Xu, Rongzhi Gu, Yuexian Zou, Peking University, China
SPE-17.3: TPARN: Triple-path attentive recurrent network for time-domain multichannel speech enhancement
Ashutosh Pandey, DeLiang Wang, The Ohio State University, United States of America; Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia, Facebook Reality Labs Research, United States of America
SPE-17.4: Multichannel Speech Enhancement without Beamforming
Ashutosh Pandey, DeLiang Wang, The Ohio State University, United States of America; Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia, Facebook Reality Labs Research, United States of America
SPE-17.5: LEARNING FILTERBANKS FOR END-TO-END ACOUSTIC BEAMFORMING
Samuele Cornell, Stefano Squartini, Università Politecnica delle Marche, Italy; Manuel Pariente, Universite de Lorraine, CNRS, Inria, LORIA,, France; François Grondin, Université de Sherbrooke, Canada
SPE-17.6: SPATIAL-TEMPORAL GRAPH CONVOLUTION NETWORK FOR MULTICHANNEL SPEECH ENHANCEMENT
Minghui Hao, Jingjing Yu, Luyao Zhang, Beijing Jiaotong University, China