@topel

Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition

, , , , , , , and . (2020)cite arxiv:2010.10504Comment: 11 pages, 3 figures, 5 tables. Submitted to NeurIPS SAS 2020 Workshop.

Abstract

We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset. More precisely, we carry out noisy student training with SpecAugment using giant Conformer models pre-trained using wav2vec 2.0 pre-training. By doing so, we are able to achieve word-error-rates (WERs) 1.4%/2.6% on the LibriSpeech test/test-other sets against the current state-of-the-art WERs 1.7%/3.3%.

Links and resources

Tags

community

  • @topel
  • @dblp
@topel's tags highlighted