TA6b4.3

Real-time Speech Enhancement and Separation with a Unified Deep Neural Network for Single/Dual Talker Scenarios

Kashyap Patel, Anton Kovalyov, Issa Panahi, University of Texas at Dallas, United States
Session:
TA6b4: Advances in Speech Processing II Poster
Track:
Speech, Image and Video Processing
Location:
Fred Farr
Presentation Time:
Tue, 31 Oct, 10:15 - 11:55 PT (UTC -8)
Session Chair:
Francesco Nespoli, Microsoft UK
Presentation
Discussion
Resources
No resources available.
Session TA6b4
TA6b4.1: Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora
Francesco Nespoli, Imperial College London / Nuance Communications UK, United Kingdom; Daniel Barreda, Nuance Communications Spain, Spain; Patrick Naylor, Imperial College London, United Kingdom
TA6b4.2: Transformer Ensemble for Synthesized Speech Detection
Emily Bartusiak, Kratika Bhagtani, Amit Kumar Singh Yadav, Edward J. Delp, Purdue University, United States
TA6b4.3: Real-time Speech Enhancement and Separation with a Unified Deep Neural Network for Single/Dual Talker Scenarios
Kashyap Patel, Anton Kovalyov, Issa Panahi, University of Texas at Dallas, United States
TA6b4.4: Binaural Speech Enhancement using Complex Convolutional Recurrent Networks
Vikas Tokala, Eric Grinstein, Mike Brookes, Imperial College London, United Kingdom; Simon Doclo, University of Oldenburg, Germany; Jesper Jensen, Demant A/S, Denmark; Patrick A. Naylor, Imperial College London, United Kingdom
Contacts