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-10: Speech Recognition 4: Transformer Models 2

Session Type: Poster
Time: Tuesday, 8 June, 16:30 - 17:15
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Yangyang Shi, Facebook AI
 
 SPE-10.1: CASS-NAT: CTC ALIGNMENT-BASED SINGLE STEP NON-AUTOREGRESSIVE TRANSFORMER FOR SPEECH RECOGNITION
         Ruchao Fan; University of California, Los Angeles
         Wei Chu; PAII Inc.
         Peng Chang; PAII Inc.
         Jing Xiao; PAII Inc.
 
 SPE-10.2: NON-AUTOREGRESSIVE TRANSFORMER ASR WITH CTC-ENHANCED DECODER INPUT
         Xingchen Song; Tsinghua University
         Zhiyong Wu; Tsinghua University
         Yiheng Huang; Tencent
         Chao Weng; Tencent
         Dan Su; Tencent
         Helen Meng; Chinese University of Hong Kong
 
 SPE-10.3: TRANSFORMER-BASED END-TO-END SPEECH RECOGNITION WITH LOCAL DENSE SYNTHESIZER ATTENTION
         Menglong Xu; Northwestern Polytechnical University
         Shengqiang Li; Northwestern Polytechnical University
         Xiao-Lei Zhang; Northwestern Polytechnical University
 
 SPE-10.4: DEVELOPING REAL-TIME STREAMING TRANSFORMER TRANSDUCER FOR SPEECH RECOGNITION ON LARGE-SCALE DATASET
         Xie Chen; Microsoft
         Yu Wu; Microsoft
         Zhenghao Wang; Microsoft
         Shujie Liu; Microsoft
         Jinyu Li; Microsoft
 
 SPE-10.5: HEAD-SYNCHRONOUS DECODING FOR TRANSFORMER-BASED STREAMING ASR
         Mohan Li; Toshiba Cambridge Research Laboratory
         Cătălin Zorilă; Toshiba Cambridge Research Laboratory
         Rama Doddipatla; Toshiba Cambridge Research Laboratory
 
 SPE-10.6: HISTORY UTTERANCE EMBEDDING TRANSFORMER LM FOR SPEECH RECOGNITION
         Keqi Deng; Institute of Acoustics, Chinese Academy of Sciences
         Gaofeng Cheng; Institute of Acoustics, Chinese Academy of Sciences
         Haoran Miao; Institute of Acoustics, Chinese Academy of Sciences
         Pengyuan Zhang; Institute of Acoustics, Chinese Academy of Sciences
         Yonghong Yan; Institute of Acoustics, Chinese Academy of Sciences