Semi-Supervised Speech Recognition via Local Prior Matching
This addresses the problem of reducing labeled data requirements for speech recognition, but it is incremental as it builds on existing knowledge distillation techniques.
The paper tackled the problem of semi-supervised speech recognition by proposing local prior matching to distill knowledge from a strong prior model, achieving 54% and 73% recovery of word error rate on clean and noisy test sets compared to a fully supervised model.
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.