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

SPE-17: Speech Enhancement 3: Target Speech Extraction

Session Type: Poster
Time: Wednesday, 9 June, 14:00 - 14:45
Location: Gather.Town
Session Chair: Dorothea Kolossa, Ruhr-Universität Bochum
 
SPE-17.1: TIME-DOMAIN SPEECH EXTRACTION WITH SPATIAL INFORMATION AND MULTI SPEAKER CONDITIONING MECHANISM
         Jisi Zhang; University of Sheffield
         Cătălin Zorilă; Toshiba Cambridge Research Laboratory
         Rama Doddipatla; Toshiba Cambridge Research Laboratory
         Jon Barker; University of Sheffield
 
SPE-17.2: ADL-MVDR: ALL DEEP LEARNING MVDR BEAMFORMER FOR TARGET SPEECH SEPARATION
         Zhuohuang Zhang; Indiana University
         Yong Xu; Tencent
         Meng Yu; Tencent
         Shi-Xiong Zhang; Tencent
         Lianwu Chen; Tencent
         Dong Yu; Tencent
 
SPE-17.3: MULTI-CHANNEL TARGET SPEECH EXTRACTION WITH CHANNEL DECORRELATION AND TARGET SPEAKER ADAPTATION
         Jiangyu Han; Shanghai Normal University
         Xinyuan Zhou; Shanghai Normal University
         Yanhua Long; Shanghai Normal University
         Yijie Li; Unisound AI Technology Co., Ltd.
 
SPE-17.4: SPEAKER ACTIVITY DRIVEN NEURAL SPEECH EXTRACTION
         Marc Delcroix; NTT Corporation
         Katerina Zmolikova; Brno University of Technology
         Tsubasa Ochiai; NTT Corporation
         Keisuke Kinoshita; NTT Corporation
         Tomohiro Nakatani; NTT Corporation
 
SPE-17.5: WASE: LEARNING WHEN TO ATTEND FOR SPEAKER EXTRACTION IN COCKTAIL PARTY ENVIRONMENTS
         Yunzhe Hao; Institute of Automation, Chinese Academy of Sciences
         Jiaming Xu; Institute of Automation, Chinese Academy of Sciences
         Peng Zhang; Institute of Automation, Chinese Academy of Sciences
         Bo Xu; Institute of Automation, Chinese Academy of Sciences
 
SPE-17.6: MULTI-STAGE SPEAKER EXTRACTION WITH UTTERANCE AND FRAME-LEVEL REFERENCE SIGNALS
         Meng Ge; Tianjin University
         Chenglin Xu; National University of Singapore
         Longbiao Wang; Tianjin University
         Eng Siong Chng; Nanyang Technological University
         Jianwu Dang; Tianjin University
         Haizhou Li; National University of Singapore