Paper ID | SPE-L3.4 |
Paper Title |
END-TO-END MULTI-SPEAKER SPEECH RECOGNITION WITH TRANSFORMER |
Authors |
Xuankai Chang, Johns Hopkins University, United States; Wangyou Zhang, Yanmin Qian, Shanghai Jiao Tong University, China; Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States; Shinji Watanabe, Johns Hopkins University, United States |
Session | SPE-L3: End-to-end Speech Recognition II: New Models |
Location | On-Demand |
Session Time: | Tuesday, 05 May, 16:30 - 18:30 |
Presentation Time: | Tuesday, 05 May, 17:30 - 17:50 |
Presentation |
Lecture
|
Topic |
Speech Processing: [SPE-LVCR] Large Vocabulary Continuous Recognition/Search |
IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
Virtual Presentation |
Click here to watch in the Virtual Conference |