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-64.3

TIME-FREQUENCY ATTENTION FOR MONAURAL SPEECH ENHANCEMENT

Qiquan Zhang, Haizhou Li, Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore; Qi Song, Alibaba Group, China, China; Zhaoheng Ni, Meta AI, United States of America; Aaron Nicolson, Australian eHealth Research Centre, CSIRO, Herston, QLD, 4006, Australia, Australia

Session:
Speech Enhancement: DNN Architectures

Track:
Speech and Language Processing

Location:
Gather Area B

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

Session Chair:
Takuya Yoshioka, Microsoft
Presentation
Discussion
Resources
Session SPE-64
SPE-64.1: MANNER: MULTI-VIEW ATTENTION NETWORK FOR NOISE ERASURE
Hyun Joon Park, Byung Ha Kang, Wooseok Shin, Jin Sob Kim, Sung Won Han, Korea University, Korea, Republic of
SPE-64.2: Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement
Guochen Yu, Communication University of China\ Institute of Acoustics, Chinese Academy of Sciences, China; Andong Li, Chengshi Zheng, Institute of Acoustics, Chinese Academy of Sciences, China; Yinuo Guo, Bytedance, China; Yutian Wang, Hui Wang, Communication University of China, China
SPE-64.3: TIME-FREQUENCY ATTENTION FOR MONAURAL SPEECH ENHANCEMENT
Qiquan Zhang, Haizhou Li, Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore; Qi Song, Alibaba Group, China, China; Zhaoheng Ni, Meta AI, United States of America; Aaron Nicolson, Australian eHealth Research Centre, CSIRO, Herston, QLD, 4006, Australia, Australia
SPE-64.4: FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
Jun Chen, Zilin Wang, Zhiyong Wu, Tsinghua University, China; Deyi Tuo, Shiyin Kang, Huya Inc., China; Helen Meng, The Chinese University of Hong Kong, China
SPE-64.5: CROSS-DOMAIN SPEECH ENHANCEMENT WITH A NEURAL CASCADE ARCHITECTURE
Heming Wang, DeLiang Wang, The Ohio State University, United States of America
SPE-64.6: SPEECH DENOISING IN THE WAVEFORM DOMAIN WITH SELF-ATTENTION
Zhifeng Kong, University of California San Diego, United States of America; Wei Ping, Ambrish Dantrey, Bryan Catanzaro, Nvidia, United States of America