Authors: Evain, Solène, Nguyen, Ha, Le, Hang, Zanon Boito, Marcely, Mdhaffar, Salima, Alisamir, Sina, Tong, Ziyi, Tomashenko, Natalia, Dinarelli, Marco, Parcollet, Titouan, Allauzen, Alexandre, Estève, Yannick, Lecouteux, Benjamin, Portet, François, Rossato, Solange, Ringeval, Fabien, Schwab, Didier, Besacier, Laurent
Venue: Interspeech 2021
Type: Publication
Abstract: Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. They were notably successful to improve performance on downstream tasks such as automatic speech recognition (ASR). While these works suggest it is possible to reduce dependence on labeled data for building efficient speech systems, their evaluation was mostly made on ASR and using multiple and heterogeneous experimental settings (most of them for English). This questi...
(read more)
Topics: 
Natural language processing
Artificial intelligence
Speech recognition
Loading (it may take a couple of seconds)...
Loading (it may take a couple of seconds)...