Technical Program

Paper Detail

Paper IDSPE-P8.4
Paper Title AUDIO-VISUAL RECOGNITION OF OVERLAPPED SPEECH FOR THE LRS2 DATASET
Authors Jianwei Yu, Chinese University of Hong Kong, Hong Kong SAR of China; Shi-Xiong Zhang, Tencent AI Lab, United States; Jian Wu, Tencent, China; Shahram Ghorbani, University of Texas at Dallas, United States; Bo Wu, Shiyin Kang, Tencent, China; Shansong Liu, Xunying Liu, Helen Meng, Chinese University of Hong Kong, Hong Kong SAR of China; Dong Yu, Tencent, United States
SessionSPE-P8: Robust Speech Recognition
LocationOn-Demand
Session Time:Wednesday, 06 May, 11:30 - 13:30
Presentation Time:Wednesday, 06 May, 11:30 - 13:30
Presentation Poster
Topic Speech Processing: [SPE-ROBU] Robust Speech Recognition
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference