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 |
|