Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2020 Open Preview.

SPE-L1: End-to-end Speech Recognition I: Streaming

Session Type: Lecture
Time: Tuesday, 5 May, 11:30 - 13:30
Location: On-Demand
Virtual Session: View on Virtual Platform
Session Chair: Shinji Watanabe, Johns Hopkins University
 
 SPE-L1.1: A STREAMING ON-DEVICE END-TO-END MODEL SURPASSING SERVER-SIDE CONVENTIONAL MODEL QUALITY AND LATENCY
         Tara Sainath; Google, Inc.
         Yanzhang He; Google, Inc.
         Bo Li; Google, Inc.
         Arun Narayanan; Google, Inc.
         Ruoming Pang; Google, Inc.
         Antoine Bruguier; Google, Inc.
         Shuo-yiin Chang; Google, Inc.
         Wei Li; Google, Inc.
         Raziel Alvarez; Google, Inc.
         Zhifeng Chen; Google, Inc.
         Chung-cheng Chiu; Google, Inc.
         David Garcia; Google, Inc.
         Alex Gruenstein; Google, Inc.
         Ke Hu; Google, Inc.
         Minho Jin; Google, Inc.
         Anjuli Kannan; Google, Inc.
         Qiao Liang; Google, Inc.
         Ian McGraw; Google, Inc.
         Cal Peyser; Google, Inc.
         Rohit Prabhavalkar; Google, Inc.
         Golan Pundak; Google, Inc.
         David Rybach; Google, Inc.
         Yuan Shangguan; Google, Inc.
         Yash Sheth; Google, Inc.
         Trevor Strohman; Google, Inc.
         Mirko Visontai; Google, Inc.
         Yonghui Wu; Google, Inc.
         Yu Zhang; Google, Inc.
         Ding Zhao; Google, Inc.
 
 SPE-L1.2: MINIMUM LATENCY TRAINING STRATEGIES FOR STREAMING SEQUENCE-TO-SEQUENCE ASR
         Hirofumi Inaguma; Kyoto University
         Yashesh Gaur; Microsoft Corporation
         Liang Lu; Microsoft Corporation
         Jinyu Li; Microsoft Corporation
         Yifan Gong; Microsoft Corporation
 
 SPE-L1.3: TOWARDS FAST AND ACCURATE STREAMING END-TO-END ASR
         Bo Li; Google, Inc.
         Shuo-Yiin Chang; Google, Inc.
         Tara Sainath; Google, Inc.
         Ruoming Pang; Google, Inc.
         Yanzhang He; Google, Inc.
         Trevor Strohman; Google, Inc.
         Yonghui Wu; Google, Inc.
 
 SPE-L1.4: STREAMING AUTOMATIC SPEECH RECOGNITION WITH THE TRANSFORMER MODEL
         Niko Moritz; Mitsubishi Electric Research Laboratories (MERL)
         Takaaki Hori; Mitsubishi Electric Research Laboratories (MERL)
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL)
 
 SPE-L1.5: CIF: CONTINUOUS INTEGRATE-AND-FIRE FOR END-TO-END SPEECH RECOGNITION
         Linhao Dong; Institute of Automation, Chinese Academy of Sciences
         Bo Xu; Institute of Automation, Chinese Academy of Sciences
 
 SPE-L1.6: TRANSFORMER-BASED ONLINE CTC/ATTENTION END-TO-END SPEECH RECOGNITION ARCHITECTURE
         Haoran Miao; Key Laboratory of Speech Acoustics and Content Understanding
         Gaofeng Cheng; Key Laboratory of Speech Acoustics and Content Understanding
         Changfeng Gao; Key Laboratory of Speech Acoustics and Content Understanding
         Pengyuan Zhang; Key Laboratory of Speech Acoustics and Content Understanding
         Yonghong Yan; Key Laboratory of Speech Acoustics and Content Understanding