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-83: New Algorithm for Speech Recognition
Fri, 13 May, 21:00 - 21:45 China Time (UTC +8)
Fri, 13 May, 13:00 - 13:45 UTC
Location: Gather Area C
Session Chair: Yanmin Qian, Shanghai Jiaotong University
Track: Speech and Language Processing

SPE-83.1: KNOWLEDGE DISTILLATION FROM LANGUAGE MODEL TO ACOUSTIC MODEL: A HIERARCHICAL MULTI-TASK LEARNING APPROACH
Munhak Lee, Joonhyuk Chang, Hanyang University, Korea, Republic of

SPE-83.2: IMPROVING PSEUDO-LABEL TRAINING FOR END-TO-END SPEECH RECOGNITION USING GRADIENT MASK
Shaoshi Ling, Chen Shen, Meng Cai, Zejun Ma, bytedance, China

SPE-83.3: MULTI-TURN RNN-T FOR STREAMING RECOGNITION OF MULTI-PARTY SPEECH
Ilya Sklyar, Anna Piunova, Amazon, Germany; Xianrui Zheng, University of Cambridge, United Kingdom of Great Britain and Northern Ireland; Yulan Liu, DeepMind, United Kingdom of Great Britain and Northern Ireland

SPE-83.4: On Language Model Integration for RNN Transducer based Speech Recognition
Wei Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney, RWTH Aachen University, Germany

SPE-83.5: CACHING NETWORKS: CAPITALIZING ON COMMON SPEECH FOR ASR
Anastasios Alexandridis, Grant Strimel, Ariya Rastrow, Pavel Kveton, Jon Webb, Maurizio Omologo, Siegfried Kunzmann, Athanasios Mouchtaris, Amazon.com, United States of America

SPE-83.6: GPU-ACCELERATED FORWARD-BACKWARD ALGORITHM WITH APPLICATION TO LATTICE-FREE MMI
Lucas Ondel, Léa-Marie Lam-Yee-Mui, Caio Corro, Laboratoire Interdisciplinaire des Sciences du Numérique, France; Martin Kocour, Lukas Burget, Brno University of Technology, France