REVIEW 1 cited by
Semi-Supervised Speech Recognition via Local Prior Matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Semi-Supervised Speech Recognition via Local Prior Matching
read the original abstract
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.
Forward citations
Cited by 1 Pith paper
-
Align-Consistency: Improving Non-autoregressive and Semi-supervised ASR with Consistency Regularization
Adding consistency regularization to every refinement step of Align-Refine reduces LibriSpeech word error rate and improves semi-supervised self-training with pseudo-labels.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.