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.

MLSP-40: Contrastive Learning

Session Type: Poster
Time: Friday, 11 June, 11:30 - 12:15
Location: Gather.Town
Virtual Session: View on Virtual Platform
Session Chair: Shuchin Aeron, Tufts University
 
 MLSP-40.1: CONTRASTIVE PREDICTIVE CODING SUPPORTED FACTORIZED VARIATIONAL AUTOENCODER FOR UNSUPERVISED LEARNING OF DISENTANGLED SPEECH REPRESENTATIONS
         Janek Ebbers; Paderborn University
         Michael Kuhlmann; Paderborn University
         Tobias Cord-Landwehr; Paderborn University
         Reinhold Haeb-Umbach; Paderborn University
 
 MLSP-40.2: CONTRASTIVE SEPARATIVE CODING FOR SELF-SUPERVISED REPRESENTATION LEARNING
         Jun Wang; Tencent
         Max W. Y. Lam; Tencent
         Dan Su; Tencent
         Dong Yu; Tencent
 
 MLSP-40.3: CONTRASTIVE SEMI-SUPERVISED LEARNING FOR ASR
         Alex Xiao; Facebook
         Christian Fuegen; Facebook
         Abdelrahman Mohamed; Facebook
 
 MLSP-40.4: CONTRASTIVE LEARNING OF GENERAL-PURPOSE AUDIO REPRESENTATIONS
         Aaqib Saeed; Eindhoven University of Technology
         David Grangier; Google Research
         Neil Zeghidour; Google Research
 
 MLSP-40.5: SEQ-CPC : SEQUENTIAL CONTRASTIVE PREDICTIVE CODING FOR AUTOMATIC SPEECH RECOGNITION
         Yulong Chen; Ping An Technology
         Jianping Zhao; Ping An Technology
         Weiqi Wang; Ping An Technology
         Ming Fang; Ping An Technology
         Haimei Kang; Ping An Technology
         Lu Wang; Ping An Technology
         Tao Wei; Ping An Technology
         Jun Ma; Ping An Technology
         Shaojun Wang; Ping An Technology
         Jing Xiao; Ping An Technology
 
 MLSP-40.6: ON SCALING CONTRASTIVE REPRESENTATIONS FOR LOW-RESOURCE SPEECH RECOGNITION
         Lasse Borgholt; University of Copenhagen
         Tycho M. S. Tax; Independent researcher (no affiliation)
         Jakob D. Havtorn; Corti
         Lars Maaløe; Corti
         Christian Igel; University of Copenhagen