2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

SPE-35: Speech Enhancement 5: DNS Challenge Task

Session Type: Poster
Time: Thursday, 10 June, 14:00 - 14:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Chandan K A Reddy, Microsoft
 
 SPE-35.1: ICASSP 2021 DEEP NOISE SUPPRESSION CHALLENGE
         Chandan Karadagur Ananda Reddy; Microsoft
         Harishchandra Dubey; Microsoft
         Vishak Gopal; Microsoft
         Ross Cutler; Microsoft
         Sebastian Braun; Microsoft
         Hannes Gamper; Microsoft
         Robert Aichner; Microsoft
         Sriram Srinivasan; Microsoft
 
 SPE-35.2: ICASSP 2021 DEEP NOISE SUPPRESSION CHALLENGE: DECOUPLING MAGNITUDE AND PHASE OPTIMIZATION WITH A TWO-STAGE DEEP NETWORK
         Andong Li; Institute of Acoustics, Chinese Academy of Sciences
         Wenzhe Liu; Institute of Acoustics, Chinese Academy of Sciences
         Xiaoxue Luo; Institute of Acoustics, Chinese Academy of Sciences
         Chengshi Zheng; Institute of Acoustics, Chinese Academy of Sciences
         Xiaodong Li; Institute of Acoustics, Chinese Academy of Sciences
 
 SPE-35.3: FULLSUBNET: A FULL-BAND AND SUB-BAND FUSION MODEL FOR REAL-TIME SINGLE-CHANNEL SPEECH ENHANCEMENT
         Xiang Hao; Inner Mongolia University & Westlake University & Westlake Institute for Advanced Study
         Xiangdong Su; Inner Mongolia University
         Radu Horaud; Inria Grenoble
         Xiaofei Li; Westlake University & Westlake Institute for Advanced Study
 
 SPE-35.4: DENSELY CONNECTED MULTI-STAGE MODEL WITH CHANNEL WISE SUBBAND FEATURE FOR REAL-TIME SPEECH ENHANCEMENT
         JingDong Li; Sogou
         Dawei Luo; Sogou
         Yun Liu; Sogou
         YuanYuan Zhu; Sogou
         Zhaoxia Li; Sogou
         Guohui Cui; Sogou
         Wenqi Tang; Sogou
         Wei Chen; Sogou
 
 SPE-35.5: A MODULATION-DOMAIN LOSS FOR NEURAL-NETWORK-BASED REAL-TIME SPEECH ENHANCEMENT
         Tyler Vuong; Carnegie Mellon University
         Yangyang Xia; Carnegie Mellon University
         Richard Stern; Carnegie Mellon University
 
 SPE-35.6: MONAURAL SPEECH ENHANCEMENT WITH COMPLEX CONVOLUTIONAL BLOCK ATTENTION MODULE AND JOINT TIME FREQUENCY LOSSES
         Shengkui Zhao; Speech Lab, Alibaba Group
         Trung Hieu Nguyen; Speech Lab, Alibaba Group
         Bin Ma; Speech Lab, Alibaba Group