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-38: Speaker Recognition 6: Self-supervised and Unsupervised Learning

Session Type: Poster
Time: Thursday, 10 June, 14:00 - 14:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Takafumi Koshinaka, Yokohama City University
 
 SPE-38.1: CONTRASTIVE SELF-SUPERVISED LEARNING FOR TEXT-INDEPENDENT SPEAKER VERIFICATION
         Haoran Zhang; Peking University
         Yuexian Zou; Peking University
         Helin Wang; Peking University
 
 SPE-38.2: ADVERSARIAL DEFENSE FOR AUTOMATIC SPEAKER VERIFICATION BY CASCADED SELF-SUPERVISED LEARNING MODELS
         Haibin Wu; National Taiwan University
         Xu Li; The Chinese University of Hong Kong
         Andy Liu; National Taiwan university
         Zhiyong Wu; Shenzhen International Graduate School, Tsinghua University
         Helen Meng; The Chinese University of Hong Kong
         Hung-yi Lee; National Taiwan University
 
 SPE-38.3: SELF-SUPERVISED TEXT-INDEPENDENT SPEAKER VERIFICATION USING PROTOTYPICAL MOMENTUM CONTRASTIVE LEARNING
         Wei Xia; University of Texas at Dallas
         Chunlei Zhang; Tencent AI Lab
         Chao Weng; Tencent AI Lab
         Meng Yu; Tencent AI Lab
         Dong Yu; Tencent AI Lab
 
 SPE-38.4: AN ITERATIVE FRAMEWORK FOR SELF-SUPERVISED DEEP SPEAKER REPRESENTATION LEARNING
         Danwei Cai; Duke University
         Weiqing Wang; Duke University
         Ming Li; Duke Kunshan University
 
 SPE-38.5: IMPROVING RECONSTRUCTION LOSS BASED SPEAKER EMBEDDING IN UNSUPERVISED AND SEMI-SUPERVISED SCENARIOS
         Jaejin Cho; Center for Language Speech Processing at Johns Hopkins University
         Piotr Zelasko; Center for Language Speech Processing at Johns Hopkins University
         Jesús Villalba; Johns Hopkins University
         Najim Dehak; Center for Language Speech Processing at Johns Hopkins University
 
SPE-38.6: NOVEL ARCHITECTURES FOR UNSUPERVISED INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION OF MEETINGS
         Nauman Dawalatabad; Indian Institute of Technology, Madras
         Srikanth Madikeri; Idiap Research Institute
         C Chandra Sekhar; Indian Institute of Technology, Madras
         Hema A Murthy; Indian Institute of Technology, Madras