ASMSP-L5.1
Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement
Haixin Zhao, Nilesh Madhu, Ghent University, Belgium
Session:
ASMSP-L5: Speech Enhancement and Dereverberation Lecture
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Teatro del Sole
Presentation Time:
Fri, 12 Sep, 10:20 - 10:40 Italy Time (UTC +2)
Presentation
Discussion
Resources
No resources available.
Session ASMSP-L5
ASMSP-L5.1: Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement
Haixin Zhao, Nilesh Madhu, Ghent University, Belgium
ASMSP-L5.2: DEEP INTERNAL LEARNING FOR SINGLE-CHANNEL SPEECH DEREVERBERATION
Yuxi Zhang, Emilie d'Olne, Vikas Tokala, Patrick A. Naylor, Imperial College London, United Kingdom
ASMSP-L5.3: DISTRIBUTED WEIGHTED PREDICTION ERROR FOR SPEECH DEREVERBERATION WITH REGULARIZATION BY DENOISING
Yibo Wang, Ziye Yang, Chengbo Chang, Jie Chen, Northwestern Polytechnical University, China
ASMSP-L5.4: VARIATIONAL AUTOENCODER FOR PERSONALIZED PATHOLOGICAL SPEECH ENHANCEMENT
Mingchi Hou, Ina Kodrasi, Idiap Research Institute, Switzerland
ASMSP-L5.5: Detection of infeasible input in speech enhancement with deep complex U-Net
Satoru Emura, Kyoto university of advanced science, Japan