GC-P13.2

THREE-STAGE BSRNN FOR UNIVERSAL SPEECH ENHANCEMENT AND DATA CURATION USING A LARGE PRE-TRAINED SPEECH RESTORATION MODEL

Ryutaro Matsunaga, Ryo Takahashi, SoftBank Corp., Japan; Shinnosuke Takamichi, Keio University, Japan
Session:
GC-P13: Universality, Robustness, and Generalizability for EnhancemeNT (URGENT) Poster
Track:
SP Grand Challenges
Location:
Poster Area 43
Presentation Time:
Fri, 8 May, 14:00 - 16:00
Presentation
Discussion
Resources
No resources available.
Session GC-P13
GC-P13.1: GAP-URGENET: A GENERATIVE-PREDICTIVE FUSION FRAMEWORK FOR UNIVERSAL SPEECH ENHANCEMENT
Xiaobin Rong, Yushi Wang, Zheng Wang, Jing Lu, Nanjing University, China
GC-P13.2: THREE-STAGE BSRNN FOR UNIVERSAL SPEECH ENHANCEMENT AND DATA CURATION USING A LARGE PRE-TRAINED SPEECH RESTORATION MODEL
Ryutaro Matsunaga, Ryo Takahashi, SoftBank Corp., Japan; Shinnosuke Takamichi, Keio University, Japan
GC-P13.3: A HYBRID DISCRIMINATIVE AND GENERATIVE SYSTEM FOR UNIVERSAL SPEECH ENHANCEMENT
Yinghao Liu, Chengwei Liu, Xiaotao Liang, Haoyin Yan, Shaofei Xue, Zheng Xue, Alibaba Group, China
GC-P13.4: HYBRID SPEECH ENHANCEMENT WITH DISCRIMINATIVE AND CODEC TOKEN PREDICTION MODELS GUIDED BY CLEANED SSL FEATURES FOR THE ICASSP 2026 URGENT CHALLENGE
Nabarun Goswami, Tatsuya Harada, The University of Tokyo, Japan
GC-P13.5: ICASSP 2026 URGENT Speech Enhancement Challenge
Chenda Li, Wei Wang, Shanghai Jiao Tong University, China; Marvin Sach, Universität Braunschweig, Germany; Wangyou Zhang, Shanghai Jiao Tong University, China; Kohei Saijo, Waseda University, Japan; Samuele Cornell, Carnegie Mellon University, United States of America; Yihui Fu, Universität Braunschweig, Germany; Zhaoheng Ni, Meta, United States of America; Tim Fingscheidt, Universität Braunschweig, Germany; Shinji Watanabe, Carnegie Mellon University, United States of America; Yanmin Qian, Shanghai Jiao Tong University, China
Contacts