Pith. sign in

REVIEW 1 cited by

Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejection

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 2201.03313 v1 pith:TXJTRAA2 submitted 2022-01-10 eess.AS cs.AIcs.SD

classification eess.AScs.AIcs.SD
keywords systemerrorpost-processingspeechcorrectioncross-modalfeatureslatency
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we propose a cross-modal post-processing system for speech recognizers, which 1) fuses acoustic features and textual features from different modalities, 2) joints a confidence estimator and an error corrector in multi-task learning fashion and 3) unifies error correction and utterance rejection modules. Compared with single-modal or single-task models, our proposed system is proved to be more effective and efficient. Experiment result shows that our post-processing system leads to more than 10% relative reduction of character error rate (CER) for both single-speaker and multi-speaker speech on our industrial ASR system, with about 1.7ms latency for each token, which ensures that extra latency introduced by post-processing is acceptable in streaming speech recognition.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR

    eess.AS 2025-05 conditional novelty 6.0 of 10

    CHSER is a new 200K-pair dataset and case study showing that fine-tuned language models can correct child ASR errors, reducing WER by up to 28.5% relative.

Pith tools