Pushing the limits of semi-supervised learning for automatic speech recognition
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%.
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%.
[CITATION][C] Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition.(2020)
Y Zhang, J Qin, DS Park, W Han, CC Chiu, R Pang… - arXiv preprint eess.AS …, 2020
Showing the best results for this search. See all results