Login Paper Search My Schedule Paper Index Help

My ICASSP 2020 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)
Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2020 Open Preview.

Clicking on the Add button next to a paper title will add that paper to your custom schedule.
Clicking on the Remove button next to a paper will remove that paper from your custom schedule.

WE1.I: Speech Recognition: Acoustic Modelling I

Session Type: Poster
Time: Wednesday, 6 May, 09:00 - 11:00
Location: On-Demand
Session Chairs: Sakriani Sakti, Nara Institute of Science and Technology / RIKEN AIP and Rohit Prabhavalkar, Google
 
   WE1.I.1: SNDCNN: SELF-NORMALIZING DEEP CNNS WITH SCALED EXPONENTIAL LINEAR UNITS FOR SPEECH RECOGNITION
         Zhen Huang; Apple
         Tim Ng; Apple
         Leo Liu; Apple
         Henry Mason; Apple
         Xiaodan Zhuang; Apple
         Daben Liu; Apple
 
   WE1.I.2: ROBUST MULTI-CHANNEL SPEECH RECOGNITION USING FREQUENCY ALIGNED NETWORK
         Taejin Park; University of Southern California
         Kenichi Kumatani; Amazon, Inc.
         Minhua Wu; Amazon, Inc.
         Shiva Sundaram; Amazon, Inc.
 
   WE1.I.3: FULLY LEARNABLE FRONT-END FOR MULTI-CHANNEL ACOUSTIC MODELING USING SEMI-SUPERVISED LEARNING
         Sanna Wager; Indiana University
         Aparna Khare; Amazon, Inc.
         Minhua Wu; Amazon, Inc.
         Kenichi Kumatani; Amazon, Inc.
         Shiva Sundaram; Amazon, Inc.
 
   WE1.I.4: G2G: TTS-DRIVEN PRONUNCIATION LEARNING FOR GRAPHEMIC HYBRID ASR
         Duc Le; Facebook
         Thilo Koehler; Facebook
         Christian Fuegen; Facebook
         Michael L. Seltzer; Facebook
 
   WE1.I.5: TRANSFORMER-BASED ACOUSTIC MODELING FOR HYBRID SPEECH RECOGNITION
         Yongqiang Wang; Facebook
         Abdelrahman Mohamed; Facebook
         Duc Le; Facebook
         Chunxi Liu; Facebook
         Alex Xiao; Facebook
         Jay Mahadeokar; Facebook
         Hongzhao Huang; Facebook
         Andros Tjandra; Facebook
         Xiaohui Zhang; Facebook
         Frank Zhang; Facebook
         Christian Fuegen; Facebook
         Geoffrey Zweig; Facebook
         Michael L. Seltzer; Facebook
 
   WE1.I.6: SPECAUGMENT ON LARGE SCALE DATASETS
         Daniel Park; Google, Inc.
         Yu Zhang; Google, Inc.
         Chung-Cheng Chiu; Google, Inc.
         Youzheng Chen; Google, Inc.
         Bo Li; Google, Inc.
         William Chan; Google, Inc.
         Quoc Le; Google, Inc.
         Yonghui Wu; Google, Inc.
 
   WE1.I.7: FAST TRAINING OF DEEP NEURAL NETWORKS FOR SPEECH RECOGNITION
         Guojing Cong; IBM
         Brian Kingsbury; IBM
         Chih-Chieh Yang; IBM
         Tianyi Liu; Georgia Institute of Technology
 
   WE1.I.8: UNSUPERVISED PRE-TRAINING OF BIDIRECTIONAL SPEECH ENCODERS VIA MASKED RECONSTRUCTION
         Weiran Wang; Amazon, Inc.
         Qingming Tang; Amazon, Inc.
         Karen Livescu; TTI-Chicago
 
   WE1.I.9: DISTILLING ATTENTION WEIGHTS FOR CTC-BASED ASR SYSTEMS
         Takafumi Moriya; NTT Corporation
         Hiroshi Sato; NTT Corporation
         Tomohiro Tanaka; NTT Corporation
         Takanori Ashihara; NTT Corporation
         Ryo Masumura; NTT Corporation
         Yusuke Shinohara; NTT Corporation
 
   WE1.I.10: DEJA-VU: DOUBLE FEATURE PRESENTATION AND ITERATED LOSS IN DEEP TRANSFORMER NETWORKS
         Andros Tjandra; Nara Institute of Science and Technology
         Chunxi Liu; Facebook AI
         Frank Zhang; Facebook AI
         Xiaohui Zhang; Facebook AI
         Yongqiang Wang; Facebook AI
         Gabriel Synnaeve; Facebook AI
         Satoshi Nakamura; Nara Institute of Science and Technology
         Geoffrey Zweig; Facebook AI
 
   WE1.I.11: FRAME-LEVEL MMI AS A SEQUENCE DISCRIMINATIVE TRAINING CRITERION FOR LVCSR
         Wilfried Michel; RWTH Aachen University
         Ralf Schl├╝ter; RWTH Aachen University
         Hermann Ney; RWTH Aachen University
 
   WE1.I.12: CROSS LINGUAL TRANSFER LEARNING FOR ZERO-RESOURCE DOMAIN ADAPTATION
         Alberto Abad; INESC-ID/IST
         Peter Bell; CSTR/University of Edinburgh
         Andrea Carmantini; CSTR/University of Edinburgh
         Steve Renals; CSTR/University of Edinburgh