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
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 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 2021 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.

SPE-9: Speech Recognition 3: Transformer Models 1

Session Type: Poster
Time: Tuesday, 8 June, 16:30 - 17:15
Location: Gather.Town
Session Chair: Yangyang Shi, Facebook AI
 
   SPE-9.1: TRANSFORMER-TRANSDUCERS FOR CODE-SWITCHED SPEECH RECOGNITION
         Siddharth Dalmia; Carnegie Mellon University
         Yuzong Liu; Amazon
         Srikanth Ronanki; Amazon
         Katrin Kirchhoff; Amazon
 
   SPE-9.2: WAKE WORD DETECTION WITH STREAMING TRANSFORMERS
         Yiming Wang; Johns Hopkins University
         Hang Lv; Northwestern Polytechnical University
         Daniel Povey; Xiaomi Corporation
         Lei Xie; Northwestern Polytechnical University
         Sanjeev Khudanpur; Johns Hopkins University
 
   SPE-9.3: CAPTURING MULTI-RESOLUTION CONTEXT BY DILATED SELF-ATTENTION
         Niko Moritz; Mitsubishi Electric Research Laboratories (MERL)
         Takaaki Hori; Mitsubishi Electric Research Laboratories (MERL)
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL)
 
   SPE-9.4: RECENT DEVELOPMENTS ON ESPNET TOOLKIT BOOSTED BY CONFORMER
         Pengcheng Guo; Northwestern Polytechnical University; Johns Hopkins University
         Florian Boyer; LaBRI, University of Bordeaux; Airudit
         Xuankai Chang; Johns Hopkins University
         Tomoki Hayashi; Nagoya University; Human Dataware Lab. Co., Ltd.
         Yosuke Higuchi; Waseda University
         Hirofumi Inaguma; Kyoto University
         Naoyuki Kamo; NTT Corporation
         Chenda Li; Shanghai Jiao Tong University
         Daniel Garcia-Romero; Johns Hopkins University
         Jiatong Shi; Johns Hopkins University
         Jing Shi; Institute of Automation, Chinese Academy of Sciences, China and Johns Hopkins University
         Shinji Watanabe; Johns Hopkins University,
         Kun Wei; Northwestern Polytechnical University
         Wangyou Zhang; Shanghai Jiao Tong University
         Yuekai Zhang; Johns Hopkins University
 
   SPE-9.5: HIERARCHICAL TRANSFORMER-BASED LARGE-CONTEXT END-TO-END ASR WITH LARGE-CONTEXT KNOWLEDGE DISTILLATION
         Ryo Masumura; NTT Corporation
         Naoki Makishima; NTT Corporation
         Mana Ihori; NTT Corporation
         Akihiko Takashima; NTT Corporation
         Tomohiro Tanaka; NTT Corporation
         Shota Orihashi; NTT Corporation
 
   SPE-9.6: END-TO-END MULTI-CHANNEL TRANSFORMER FOR SPEECH RECOGNITION
         Feng-Ju Chang; Amazon
         Martin Radfar; Amazon
         Athanasios Mouchtaris; Amazon
         Brian King; Amazon
         Siegfried Kunzmann; Amazon