Papers › Semi-Supervised Speech Recognition via Local Prior Matching

Semi-Supervised Speech Recognition via Local Prior Matching

24 Feb 2020arXiv:2002.10336archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

facebookresearch/wav2letter mentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Knowledge DistillationLanguage ModelingLanguage ModellingSpeech Recognitionspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition LibriSpeech test-clean Local Prior Matching (Large Model) Word Error Rate (WER) 7.19 #62 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other Local Prior Matching (Large Model, ConvLM LM) Word Error Rate (WER) 15.28 #51 of 53 Archive leaderboard report
Speech Recognition LibriSpeech test-other Local Prior Matching (Large Model) Word Error Rate (WER) 20.84 #53 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: LPM

Knowledge DistillationLPMTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections