AUD-28.5
CATEGORY-ADAPTED SOUND EVENT ENHANCEMENT WITH WEAKLY LABELED DATA
Guangwei Li, Xuenan Xu, Mengyue Wu, Kai Yu, Shanghai Jiao Tong University, China; Heinrich Dinkel, Xiaomi Corporation, China
Session:
Signal Enhancement and Restoration II
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area L
Presentation Time:
Thu, 12 May, 21:00 - 21:45 China Time (UTC +8)
Thu, 12 May, 13:00 - 13:45 UTC
Thu, 12 May, 13:00 - 13:45 UTC
Session Chair:
Hirokazu Kameoka, NTT Communication Science Laboratories, Tokyo
Session AUD-28
AUD-28.1: POSTGAN: A GAN-BASED POST-PROCESSOR TO ENHANCE THE QUALITY OF CODED SPEECH
Srikanth Korse, Nicola Pia, Kishan Gupta, Guillaume Fuchs, Fraunhofer IIS, Erlangen, Germany, Germany
AUD-28.2: A DNN BASED POST-FILTER TO ENHANCE THE QUALITY OF CODED SPEECH IN MDCT DOMAIN
Kishan Gupta, Srikanth Korse, Bernd Edler, Guillaume Fuchs, Fraunhofer IIS, Germany
AUD-28.3: A TWO-STAGE U-NET FOR HIGH-FIDELITY DENOISING OF HISTORICAL RECORDINGS
Eloi Moliner, Vesa Välimäki, Aalto University, Finland
AUD-28.4: EXPERTS VERSUS ALL-ROUNDERS: TARGET LANGUAGE EXTRACTION FOR MULTIPLE TARGET LANGUAGES
Marvin Borsdorf, Kevin Scheck, Tanja Schultz, University of Bremen, Germany; Haizhou Li, National University of Singapore, Singapore
AUD-28.5: CATEGORY-ADAPTED SOUND EVENT ENHANCEMENT WITH WEAKLY LABELED DATA
Guangwei Li, Xuenan Xu, Mengyue Wu, Kai Yu, Shanghai Jiao Tong University, China; Heinrich Dinkel, Xiaomi Corporation, China
AUD-28.6: SEQUENTIAL MCMC METHODS FOR AUDIO SIGNAL ENHANCEMENT
Ruben Claveria, Simon Godsill, University of Cambridge, United Kingdom of Great Britain and Northern Ireland