English

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction

Audio and Speech Processing 2021-04-28 v1 Computation and Language Machine Learning Sound

Abstract

Confidence scores are very useful for downstream applications of automatic speech recognition (ASR) systems. Recent works have proposed using neural networks to learn word or utterance confidence scores for end-to-end ASR. In those studies, word confidence by itself does not model deletions, and utterance confidence does not take advantage of word-level training signals. This paper proposes to jointly learn word confidence, word deletion, and utterance confidence. Empirical results show that multi-task learning with all three objectives improves confidence metrics (NCE, AUC, RMSE) without the need for increasing the model size of the confidence estimation module. Using the utterance-level confidence for rescoring also decreases the word error rates on Google's Voice Search and Long-tail Maps datasets by 3-5% relative, without needing a dedicated neural rescorer.

Keywords

Cite

@article{arxiv.2104.12870,
  title  = {Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction},
  author = {David Qiu and Yanzhang He and Qiujia Li and Yu Zhang and Liangliang Cao and Ian McGraw},
  journal= {arXiv preprint arXiv:2104.12870},
  year   = {2021}
}

Comments

Submitted to Interspeech 2021

R2 v1 2026-06-24T01:32:35.216Z