For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose local prior matching (LPM), a semi-supervised objective that distills knowledge from a strong prior (e.g. a language model) to provide learning signal to a discriminative model trained on unlabeled speech. We demonstrate that LPM is theoretically well-motivated, simple to implement, and superior to existing knowledge distillation techniques under comparable settings. Starting from a baseline trained on 100 hours of labeled speech, with an additional 360 hours of unlabeled data, LPM recovers 54% and 73% of the word error rate on clean and noisy test sets relative to a fully supervised model on the same data.
@article{arxiv.2002.10336,
title = {Semi-Supervised Speech Recognition via Local Prior Matching},
author = {Wei-Ning Hsu and Ann Lee and Gabriel Synnaeve and Awni Hannun},
journal= {arXiv preprint arXiv:2002.10336},
year = {2020}
}