2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Click on the icon to view the manuscript on IEEE XPlore in the IEEE ICASSP 2021 Open Preview.

SPE-52: Speech Enhancement 8: Echo Cancellation and Other Tasks

Session Type: Poster
Time: Friday, 11 June, 13:00 - 13:45
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Ann Spriet, GOODIX Technology Inc.
 
 SPE-52.1: A NEURAL ACOUSTIC ECHO CANCELLER OPTIMIZED USING AN AUTOMATIC SPEECH RECOGNIZER AND LARGE SCALE SYNTHETIC DATA
         Nathan Howard; Google
         Alex Park; Google
         Turaj Shabestary; Google
         Alexander Gruenstein; Google
         Rohit Prabhavalkar; Google
 
 SPE-52.2: LOW-COMPLEXITY, REAL-TIME JOINT NEURAL ECHO CONTROL AND SPEECH ENHANCEMENT BASED ON PERCEPNET
         Jean-Marc Valin; Amazon
         Srikanth Tenneti; Amazon
         Karim Helwani; Amazon
         Umut Isik; Amazon
         Arvindh Krishnaswamy; Amazon
 
 SPE-52.3: ACOUSTIC ECHO CANCELLATION WITH THE DUAL-SIGNAL TRANSFORMATION LSTM NETWORK
         Nils L. Westhausen; Carl von Ossietzky University
         Bernd T. Meyer; Carl von Ossietzky University
 
 SPE-52.4: HIGH FIDELITY SPEECH REGENERATION WITH APPLICATION TO SPEECH ENHANCEMENT
         Adam Polyak; Tel Aviv University; Facebook
         Lior Wolf; Tel Aviv University; Facebook
         Yossi Adi; Facebook
         Ori Kabeli; Facebook
         Yaniv Taigman; Facebook
 
 SPE-52.5: A TIME-DOMAIN CONVOLUTIONAL RECURRENT NETWORK FOR PACKET LOSS CONCEALMENT
         Ju Lin; Clemson University
         Yun Wang; Facebook AI
         Kaustubh Kalgaonkar; Facebook AI
         Gil Keren; Facebook AI
         Didi Zhang; Facebook AI
         Christian Fuegen; Facebook AI
 
 SPE-52.6: CASCADED TIME + TIME-FREQUENCY UNET FOR SPEECH ENHANCEMENT: JOINTLY ADDRESSING CLIPPING, CODEC DISTORTIONS, AND GAPS
         Arun Asokan Nair; Johns Hopkins University
         Kazuhito Koishida; Microsoft Corporation