Semi-Supervised Speech Recognition via Local Prior Matching

24 Feb 2020  ·  Wei-Ning Hsu, Ann Lee, Gabriel Synnaeve, Awni Hannun ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Speech Recognition LibriSpeech test-clean Local Prior Matching (Large Model) Word Error Rate (WER) 7.19 # 47
Speech Recognition LibriSpeech test-other Local Prior Matching (Large Model) Word Error Rate (WER) 20.84 # 42
Speech Recognition LibriSpeech test-other Local Prior Matching (Large Model, ConvLM LM) Word Error Rate (WER) 15.28 # 40

Methods