English

Multitask Training with Text Data for End-to-End Speech Recognition

Computation and Language 2021-06-15 v2

Abstract

We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only data. Trained on the 100-hour subset of LibriSpeech, the proposed method, without requiring an additional language model, leads to an 11% relative performance improvement over the baseline and approaches the performance of language model shallow fusion on the test-clean evaluation set. We observe a similar trend on the whole 960-hour LibriSpeech training set. Analyses of different types of errors and sample output sentences demonstrate that the proposed method can incorporate language level information, suggesting its effectiveness in real-world applications.

Keywords

Cite

@article{arxiv.2010.14318,
  title  = {Multitask Training with Text Data for End-to-End Speech Recognition},
  author = {Peidong Wang and Tara N. Sainath and Ron J. Weiss},
  journal= {arXiv preprint arXiv:2010.14318},
  year   = {2021}
}
R2 v1 2026-06-23T19:41:17.491Z