2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
MLSP-11: Self-supervised Learning for Speech Processing |
| Session Type: Poster |
| Time: Tuesday, 8 June, 16:30 - 17:15 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Isabel Trancoso, INESC-ID / IST, University of Lisbon |
| 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 |