IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
SPE-79.1

TRANSFORMER-BASED STREAMING ASR WITH CUMULATIVE ATTENTION

Mohan Li, Shucong Zhang, Cătălin Zorilă, Rama Doddipatla, Toshiba Cambridge Research Laboratory, Toshiba Europe Ltd, United Kingdom of Great Britain and Northern Ireland

Session:
Speech Recognition: Transformers

Track:
Speech and Language Processing

Location:
Gather Area C

Presentation Time:
Fri, 13 May, 20:00 - 20:45 China Time (UTC +8)
Fri, 13 May, 12:00 - 12:45 UTC

Session Chair:
Yangyang Shi, Meta
Presentation
Discussion
Resources
Session SPE-79
SPE-79.1: TRANSFORMER-BASED STREAMING ASR WITH CUMULATIVE ATTENTION
Mohan Li, Shucong Zhang, Cătălin Zorilă, Rama Doddipatla, Toshiba Cambridge Research Laboratory, Toshiba Europe Ltd, United Kingdom of Great Britain and Northern Ireland
SPE-79.2: STREAMING TRANSFORMER TRANSDUCER BASED SPEECH RECOGNITION USING NON-CAUSAL CONVOLUTION
Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer, Facebook AI, United States of America
SPE-79.3: HYBRID RNN-T/ATTENTION-BASED STREAMING ASR WITH TRIGGERED CHUNKWISE ATTENTION AND DUAL INTERNAL LANGUAGE MODEL INTEGRATION
Takafumi Moriya, Takanori Ashihara, Atsushi Ando, Hiroshi Sato, Tomohiro Tanaka, Kohei Matsuura, Ryo Masumura, Marc Delcroix, NTT Corporation, Japan; Takahiro Shinozaki, Tokyo Institute of Technology, Japan
SPE-79.4: RUN-AND-BACK STITCH SEARCH: NOVEL BLOCK SYNCHRONOUS DECODING FOR STREAMING ENCODER-DECODER ASR
Emiru Tsunoo, Michael Hentschel, Yosuke Kashiwagi, Sony Group Corporation, Japan; Chaitanya Narisetty, Shinji Watanabe, Carnegie Mellon University, United States of America
SPE-79.5: Alignment-Learning based single-step decoding for accurate and fast non-autoregressive speech recognition
Yonghe Wang, Rui Liu, Feilong Bao, Hui Zhang, Guanglai Gao, Inner Mongolia University, China
SPE-79.6: USTED: IMPROVING ASR WITH A UNIFIED SPEECH AND TEXT ENCODER-DECODER
Bolaji Yusuf, Bogazici University, Turkey; Ankur Gandhe, Alex Sokolov, Amazon, United States of America