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
AUD-6: Audio Security and Multi-Modal Systems
Sun, 8 May, 23:00 - 23:45 China Time (UTC +8)
Sun, 8 May, 15:00 - 15:45 UTC
Location: Gather Area K
Session Chair: Hung-Yi Lee, National Taiwan University
Track: Audio and Acoustic Signal Processing

AUD-6.1: On Adversarial Robustness of Large-scale Audio Visual Learning
Juncheng B Li, Xinjian Li, Po-Yao (Bernie) Huang, Florian Metze, Carnegie Mellon University, United States of America; Shuhui Qu, Stanford University, United States of America

AUD-6.2: Adversarial sample detection for speaker verification by neural vocoders
Haibin Wu, Po-chun Hsu, Hung-yi Lee, National Taiwan University, China; Ji Gao, Shanshan Zhang, Shen Huang, Jian Kang, Tencent, China; Zhiyong Wu, Shenzhen International Graduate School, Tsinghua University, China; Helen Meng, The Chinese University of Hong Kong, Hong Kong

AUD-6.3: SOURCE MIXING AND SEPARATION ROBUST AUDIO STEGANOGRAPHY
Naoya Takahashi, Mayank Kumar Singh, Yuki Mitsufuji, Sony Group Corporation, Japan

AUD-6.4: MULTI-MODAL PRE-TRAINING FOR AUTOMATED SPEECH RECOGNITION
David Chan, University of California, Berkeley, United States of America; Shalini Ghosh, Debmalya Chakrabarty, Björn Hoffmeister, Amazon, United States of America

AUD-6.5: SPEAKER-TARGETED AUDIO-VISUAL SPEECH RECOGNITION USING A HYBRID CTC/ATTENTION MODEL WITH INTERFERENCE LOSS
Ryota Tsunoda, Ryoichi Takashima, Tetsuya Takiguchi, Kobe University, Japan; Ryo Aihara, Yoshie Imai, Mitsubishi Electric Corporation, Japan

AUD-6.6: TIME-DOMAIN AUDIO-VISUAL SPEECH SEPARATION ON LOW QUALITY VIDEOS
Yifei Wu, Chenda Li, Yanmin Qian, Shanghai Jiao Tong University, China; Jinfeng Bai, Zhongqin Wu, TAL Education Group, China, China