Technical Program

Paper Detail

Session:New Features, Models and Representations / Audio Visual ASR
Location:Poster Area A, Ground Floor
Session Time:Thursday, May 16, 13:00 - 15:00
Presentation Time:Thursday, May 16, 13:00 - 15:00
Presentation: Poster
Topic: Speech Processing: General Topics in Speech Recognition
Paper Title: Robust Audio-Visual Speech Recognition Using Bimodal DFSMN with Multi-condition Training and Dropout Regularization
Manuscript Link:  Click here to view manuscript on IEEE Xplore
Authors: Shiliang Zhang, Ming Lei, Bin Ma, Machine Intelligence Technology, Alibaba Group, China; Lei Xie, Northwestern Polytechnical University, China