TU2.AUD.1
Universal Sound Separation with Self-Supervised Audio Masked Autoencoder
Junqi Zhao, Xubo Liu, Jinzheng Zhao, Yi Yuan, University of Surrey, United Kingdom; Qiuqiang Kong, The Chinese University of Hong Kong, China; Mark Plumbley, Wenwu Wang, University of Surrey, United Kingdom
Session:
TU2.AUD: Enhancement and Separation of Audio and Speech Lecture
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Auditorium
Presentation Time:
Tue, 27 Aug, 14:30 - 14:50 France Time (UTC +1)
Session Chair:
Nobutaka Ono, Tokyo Metropolitan University
Presentation
Discussion
Resources
No resources available.
Session TU2.AUD
TU2.AUD.1: Universal Sound Separation with Self-Supervised Audio Masked Autoencoder
Junqi Zhao, Xubo Liu, Jinzheng Zhao, Yi Yuan, University of Surrey, United Kingdom; Qiuqiang Kong, The Chinese University of Hong Kong, China; Mark Plumbley, Wenwu Wang, University of Surrey, United Kingdom
TU2.AUD.2: McRTSE: Multi-channel Reverberant Target Sound Extraction
Shrishail Baligar, Shawn Newsam, University of California, Merced, United States
TU2.AUD.3: CASCADED NOISE REDUCTION AND ACOUSTIC ECHO CANCELLATION BASED ON AN EXTENDED NOISE REDUCTION
Arnout Roebben, Toon van Waterschoot, Marc Moonen, KU Leuven, Belgium
TU2.AUD.4: SPECTRUM-AWARE NEURAL VOCODER BASED ON SELF-SUPERVISED LEARNING FOR SPEECH ENHANCEMENT
Yanjue Song, Ghent University - imec, Belgium; Doyeon Kim, Hong-Goo Kang, Yonsei University, Korea (South); Nilesh Madhu, Ghent University - imec, Belgium
TU2.AUD.5: Hallucination in Perceptual Metric-Driven Speech Enhancement Networks
George Close, Thomas Hain, Stefan Goetze, University of Sheffield, United Kingdom