Pith. sign in

REVIEW

Token-Weighted RNN-T for Learning from Flawed Data

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

arxiv 2406.18108 v1 pith:SJCU6OKI submitted 2024-06-26 cs.CL cs.LGcs.SDeess.AS

classification cs.CLcs.LGcs.SDeess.AS
keywords accuracyrnn-terrorstoken-weightedcriteriondatadegradationlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the target sequence is sensible, one may want to de-emphasize tokens that reflect transcription errors. In this work, we propose a novel token-weighted RNN-T criterion that augments the RNN-T objective with token-specific weights. The new objective is used for mitigating accuracy loss from transcriptions errors in the training data, which naturally appear in two settings: pseudo-labeling and human annotation errors. Experiments results show that using our method for semi-supervised learning with pseudo-labels leads to a consistent accuracy improvement, up to 38% relative. We also analyze the accuracy degradation resulting from different levels of WER in the reference transcription, and show that token-weighted RNN-T is suitable for overcoming this degradation, recovering 64%-99% of the accuracy loss.

Discussion (0). Sign in to comment.

Pith tools