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
ASML-CN1: Audio Signal Processing and Machine Learning
Fri, 28 Oct, 13:00 - 15:00 China Time (UTC +8)
Fri, 28 Oct, 05:00 - 07:00 UTC
Location: Lotus Room, Level 2
Track: Audio and Acoustic Signal Processing

ASML-CN1.1: DIVERSITY-CONTROLLABLE AND ACCURATE AUDIO CAPTIONING BASED ON NEURAL CONDITION

Xuenan Xu, Mengyue Wu, Kai Yu, Shanghai Jiao Tong University, China

ASML-CN1.2: TEA-PSE: TENCENT-ETHEREAL-AUDIO-LAB PERSONALIZED SPEECH ENHANCEMENT SYSTEM FOR ICASSP 2022 DNS CHALLENGE

Yukai Ju, Xiaopeng Yan, Yihui Fu, Shubo Lv, Luyao Cheng, Lei Xie, Northwestern Polytechnical University, China; Wei Rao, Yannan Wang, Shidong Shang, Tencent, China

ASML-CN1.4: A COMPLEX SPECTRAL MAPPING WITH INPLACE CONVOLUTION RECURRENT NEURAL NETWORKS FOR ACOUSTIC ECHO CANCELLATION

Chenggang Zhang, Jinjiang Liu, Xueliang Zhang, Inner Mongolia University, China

ASML-CN1.5: DRC-NET: DENSELY CONNECTED RECURRENT CONVOLUTIONAL NEURAL NETWORK FOR SPEECH DEREVERBERATION

Jinjiang Liu, Xueliang Zhang, College of Computer Science, Inner Mongolia University, China

ASML-CN1.6: Multitask Gaussian Process with Hierarchical Latent Interactions

Kai Chen, Feng Yin, Shuguang Cui, The Chinese University of Hong Kong, Shenzhen, China; Twan van Laarhoven, Elena Marchiori, Radboud University, Nijmegen, Netherlands

ASML-CN1.7: NEIGHBOR-AUGMENTED TRANSFORMER-BASED EMBEDDING FOR RETRIEVAL

Jihai Zhang, Fangquan Lin, Wei Jiang, Cheng Yang, Alibaba Group, China; Gaoge Liu, Columbia University, United States of America

ASML-CN1.8: A Byzantine-resilient Dual Subgradient Method for Vertical Federated Learning

Kun Yuan, Alibaba Group (US), United States of America; Zhaoxian Wu, Qing Ling, Sun Yat-Sen University, China