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

MLSP-11: Self-supervised Learning for Speech Processing

Session Type: Poster
Time: Tuesday, 8 June, 16:30 - 17:15
Location: Gather.Town
Session Chair: Zheng-Hua Tan, Aalborg University
 
MLSP-11.1: NEURAL AUDIO FINGERPRINT FOR HIGH-SPECIFIC AUDIO RETRIEVAL BASED ON CONTRASTIVE LEARNING
         Sungkyun Chang; Cochlear.ai
         Donmoon Lee; Cochlear.ai, Seoul National University
         Jeongsoo Park; Cochlear.ai
         Hyungui Lim; Cochlear.ai
         Kyogu Lee; Seoul National University
         Karam Ko; SK Telecom
         Yoonchang Han; Cochlear.ai
 
MLSP-11.2: SELF-TRAINING AND PRE-TRAINING ARE COMPLEMENTARY FOR SPEECH RECOGNITION
         Qiantong Xu; Facebook AI Research
         Alexei Baevski; Facebook AI Research
         Tatiana Likhomanenko; Facebook AI Research
         Paden Tomasello; Facebook AI Research
         Alexis Conneau; Facebook AI Research
         Ronan Collobert; Facebook AI Research
         Gabriel Synnaeve; Facebook AI Research
         Michael Auli; Facebook AI Research
 
MLSP-11.3: UNSUPERVISED DISCRIMINATIVE LEARNING OF SOUNDS FOR AUDIO EVENT CLASSIFICATION
         Sascha Hornauer; University of California, Berkeley
         Ke Li; University of California, Berkeley
         Stella Yu; University of California, Berkeley
         Shabnam Ghaffarzadegan; Robert Bosch LLC
         Liu Ren; Robert Bosch LLC
 
MLSP-11.4: SIMILARITY ANALYSIS OF SELF-SUPERVISED SPEECH REPRESENTATIONS
         Yu-An Chung; Massachusetts Institute of Technology
         Yonatan Belinkov; Technion Henry and Marilyn Taub Faculty of Computer Science
         James Glass; Massachusetts Institute of Technology
 
MLSP-11.5: JOINT MASKED CPC AND CTC TRAINING FOR ASR
         Chaitanya Talnikar; Facebook
         Tatiana Likhomanenko; Facebook
         Ronan Collobert; Facebook
         Gabriel Synnaeve; Facebook
 
MLSP-11.6: A COMPARISON OF DISCRETE LATENT VARIABLE MODELS FOR SPEECH REPRESENTATION LEARNING
         Henry Zhou; University of Toronto
         Alexei Baevski; Facebook AI Research
         Michael Auli; Facebook AI Research