SLP-P37: Speech enhancement and separation III
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)
Location: Poster Zone 4B
Session Type: Poster
Session Co-Chairs: Li Li, CyberAgent, Inc. and Takuya Yoshioka, AssemblyAI
Track: Speech and Language Processing
Click the to view the manuscript on IEEE Xplore Open Preview
 

SLP-P37.1: HOW DOES END-TO-END SPEECH RECOGNITION TRAINING IMPACT SPEECH ENHANCEMENT ARTIFACTS?
Kazuma Iwamoto, Doshisha University, Japan; Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, NTT Corporation, Japan; Shigeru Katagiri, Doshisha University, Japan

SLP-P37.2: INTER-FREQUENCY PHASE DIFFERENCE FOR PHASE RECONSTRUCTION USING DEEP NEURAL NETWORKS AND MAXIMUM LIKELIHOOD
Binh Thien Nguyen, Ritsumeikan University, Japan; Yukoh Wakabayashi, Toyohashi University of Technology, Japan; Kenta Iwai, Takanobu Nishiura, Ritsumeikan University, Japan
 

SLP-P37.3: AN END-TO-END EEG CHANNEL SELECTION METHOD WITH RESIDUAL GUMBEL SOFTMAX FOR BRAIN-ASSISTED SPEECH ENHANCEMENT
Qing-Tian Xu, Jie Zhang, Zhen-Hua Ling, University of Science and Technology of China, China
 

SLP-P37.4: MOSSFORMER2: COMBINING TRANSFORMER AND RNN-FREE RECURRENT NETWORK FOR ENHANCED TIME-DOMAIN MONAURAL SPEECH SEPARATION
Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Jia Qi Yip, Dianwen Ng, Bin Ma, Alibaba Group, Singapore
 

SLP-P37.5: WHAT DO NEURAL NETWORKS LISTEN TO? EXPLORING THE CRUCIAL BANDS IN SPEECH ENHANCEMENT USING SINC-CONVOLUTION
Kuan-Hsun Ho, National Taiwan Normal University, Taiwan; Jeih-weih Hung, National Chi Nan University, Taiwan; Berlin Chen, National Taiwan Normal University, Taiwan
 

SLP-P37.6: Hybrid Attention Time-Frequency Analysis Network for Single-Channel Speech Enhancement
Zehua Zhang, Xingwei Liang, Ruifeng Xu, Mingjiang Wang, Harbin Institute of Technology (Shenzhen), China
 

SLP-P37.7: SPEAKER ADAPTATION FOR ENHANCEMENT OF BONE-CONDUCTED SPEECH
Amin Edraki, Wai-Yip Chan, Queen’s University, Canada; Jesper Jensen, Demant A/S, Denmark; Daniel Fogerty, University of Illinois Urbana-Champaign, United States of America
 

SLP-P37.8: A weighted-variance variational autoencoder model for speech enhancement
Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel, Inria, France
 

SLP-P37.9: Posterior Sampling Algorithms for Unsupervised Speech Enhancement with Recurrent Variational Autoencoder
Mostafa Sadeghi, Romain Serizel, Inria, France
 

SLP-P37.10: A SEPARATION PRIORITY PIPELINE FOR SINGLE-CHANNEL SPEECH SEPARATION IN NOISY ENVIRONMENTS
Shaoxiang Dang, Tetsuya Matsumoto, Nagoya University, Japan; Yoshinori Takeuchi, Daido University, Japan; Hiroaki Kudo, Nagoya University, Japan