SLP-P3.3
An Efficient and Interpretable Speech Enhancement Network via Deep Dictionary Learning
Xinmeng Xu, Yiqun Zhang, Weiping Tu, Yuhong Yang, Wuhan University, China
Session:
SLP-P3: Speech enhancement and separation I Poster
Track:
Speech and Language Processing
Location:
Poster Zone 1A
Poster Board PZ-1A.3
Poster Board PZ-1A.3
Presentation Time:
Wed, 17 Apr, 08:20 - 10:20 (UTC +9)
Session Co-Chairs:
Zheng-Hua Tan, Aalborg University and Tsubasa Ochiai, NTT Corporation
Session SLP-P3
SLP-P3.1: TWO-STEP KNOWLEDGE DISTILLATION FOR TINY SPEECH ENHANCEMENT
Rayan Daod Nathoo, Mikolaj Kegler, Marko Stamenovic, Bose Corp., United States of America
SLP-P3.2: ON REAL-TIME MULTI-STAGE SPEECH ENHANCEMENT SYSTEMS
Lingjun Meng, Jozef Coldenhoff, Ecole Polytechnique Federale de Lausanne, Switzerland; Paul Kendrick, Tijana Stojkovic, Andrew Harper, Kiril Ratmanski, Milos Cernak, Logitech Europe S.A., Switzerland
SLP-P3.3: An Efficient and Interpretable Speech Enhancement Network via Deep Dictionary Learning
Xinmeng Xu, Yiqun Zhang, Weiping Tu, Yuhong Yang, Wuhan University, China
SLP-P3.4: SICRN: ADVANCING SPEECH ENHANCEMENT THROUGH STATE SPACE MODEL AND INPLACE CONVOLUTION TECHNIQUES
Changjiang Zhao, Shulin He, Xueliang Zhang, Inner Mongolia University, China
SLP-P3.5: Lightweight Multi-Axial Transformer with Frequency Prompt for Single Channel Speech Enhancement
Xingwei Liang, Zehua Zhang, Mingjiang Wang, Ruifeng Xu, Harbin Institute of Technology (Shenzhen), Armenia
SLP-P3.6: FSPEN: AN ULTRA-LIGHTWEIGHT NETWORK FOR REAL TIME SPEECH ENAHNCMENT
Lei Yang, Wei Liu, Ruijie Meng, Gunwoo Lee, Soonho Baek, Han-gil Moon, Samsung, China
SLP-P3.7: IMPROVING DESIGN OF INPUT CONDITION INVARIANT SPEECH ENHANCEMENT
Wangyou Zhang, Shanghai Jiao Tong University, China; Jee-weon Jung, Carnegie Mellon University, United States of America; Yanmin Qian, Shanghai Jiao Tong University, China
SLP-P3.8: ON THE IMPORTANCE OF NEURAL WIENER FILTER FOR RESOURCE EFFICIENT MULTICHANNEL SPEECH ENHANCEMENT
Tsun-An Hsieh, Indiana University Bloomington, United States of America; Jacob Donley, Daniel Wong, Buye Xu, Ashutosh Pandey, Reality Labs Research at Meta, United States of America
SLP-P3.9: DECOUPLED SPATIAL AND TEMPORAL PROCESSING FOR RESOURCE EFFICIENT MULTICHANNEL SPEECH ENHANCEMENT
Ashutosh Pandey, Buye Xu, Meta, United States of America
SLP-P3.10: Complexity Scaling for Speech Denoising
Hangting Chen, Jianwei Yu, Chao Weng, Tencent, China
SLP-P3.11: A TWO-STAGE FRAMEWORK IN CROSS-SPECTRUM DOMAIN FOR REAL-TIME SPEECH ENHANCEMENT
Yuewei Zhang, Shanghai Jiao Tong University, China; Huanbin Zou, Tencent, China; Jie Zhu, Shanghai Jiao Tong University, China
Contacts