Semi-Supervised Speech Recognition via Local Prior Matching
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 AbstractCode
Datasets
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
---|---|---|---|---|---|---|---|
Speech Recognition | LibriSpeech test-clean | Local Prior Matching (Large Model) | Word Error Rate (WER) | 7.19 | # 53 | ||
Speech Recognition | LibriSpeech test-other | Local Prior Matching (Large Model) | Word Error Rate (WER) | 20.84 | # 47 | ||
Speech Recognition | LibriSpeech test-other | Local Prior Matching (Large Model, ConvLM LM) | Word Error Rate (WER) | 15.28 | # 45 |