Technical Program

SLP-P23: End-to-end Speech Recognition V: Modeling Methods

Session Type: Poster
Time: Friday, May 17, 16:00 - 18:00
Location: Poster Area A, Ground Floor
Session Chair: Gakuto Kurata, IBM
 
SLP-P23.1: END-TO-END SPEECH RECOGNITION USING A HIGH RANK LSTM-CTC BASED MODEL
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Yangyang Shi; Mobvoi AI Lab
         Mei-Yuh Hwang; Mobvoi AI Lab
         Xin Lei; Mobvoi AI Lab
 
SLP-P23.2: INVESTIGATION OF MODELING UNITS FOR MANDARIN SPEECH RECOGNITION USING DFSMN-CTC-SMBR
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Shiliang Zhang; Machine Intelligence Technology, Alibaba Group
         Ming Lei; Machine Intelligence Technology, Alibaba Group
         Yuan Liu; Machine Intelligence Technology, Alibaba Group
         Wei Li; Machine Intelligence Technology, Alibaba Group
 
SLP-P23.3: END-TO-END ANCHORED SPEECH RECOGNITION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Yiming Wang; Johns Hopkins University
         Xing Fan; Amazon
         I-Fan Chen; Amazon
         Yuzong Liu; Amazon
         Tongfei Chen; Johns Hopkins University
         Björn Hoffmeister; Amazon
 
SLP-P23.4: THE SPEECHTRANSFORMER FOR LARGE-SCALE MANDARIN CHINESE SPEECH RECOGNITION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Yuanyuan Zhao; Kwai
         Jie Li; Kwai
         Xiaorui Wang; Kwai
         Yan Li; Kwai
 
SLP-P23.5: WINDOWED ATTENTION MECHANISMS FOR SPEECH RECOGNITION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Shucong Zhang; University of Edinburgh
         Erfan Loweimi; University of Edinburgh
         Peter Bell; University of Edinburgh
         Steve Renals; University of Edinburgh
 
SLP-P23.6: STREAM ATTENTION-BASED MULTI-ARRAY END-TO-END SPEECH RECOGNITION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Xiaofei Wang; Johns Hopkins University
         Ruizhi Li; Johns Hopkins University
         Sri Harish Mallidi; Amazon
         Takaaki Hori; Mitsubishi Electric Research Laboratories
         Shinji Watanabe; Johns Hopkins University
         Hynek Hermansky; Johns Hopkins University
 
SLP-P23.7: IMPROVING END-TO-END SPEECH RECOGNITION WITH PRONUNCIATION-ASSISTED SUB-WORD MODELING
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Hainan Xu; Johns Hopkins University
         Shuoyang Ding; Johns Hopkins University
         Shinji Watanabe; Johns Hopkins University
 
SLP-P23.8: SELF-ATTENTION NETWORKS FOR CONNECTIONIST TEMPORAL CLASSIFICATION IN SPEECH RECOGNITION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Julian Salazar; Amazon AI
         Katrin Kirchhoff; Amazon AI
         Zhiheng Huang; Amazon AI
 
SLP-P23.9: SEMANTIC QUERY-BY-EXAMPLE SPEECH SEARCH USING VISUAL GROUNDING
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Herman Kamper; Stellenbosch University
         Aristotelis Anastassiou; Stellenbosch University
         Karen Livescu; TTI-Chicago