Publication detail

Usted: Improving ASR with a Unified Speech and Text Encoder-Decoder

YUSUF, B. GANDHE, A. SOKOLOV, A.

Original Title

Usted: Improving ASR with a Unified Speech and Text Encoder-Decoder

Type

conference paper

Language

English

Original Abstract

Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without incurring the extra cost of evaluating an external language model at inference time. In this work, we propose training ASR model jointly with a set of text-to-text auxiliary tasks with which it shares a decoder and parts of the encoder. When we jointly train ASR and masked language model with the 960-hour Librispeech and Opensubtitles data respectively, we observe WER reductions of 16% and 20% on test-other and test-clean respectively over an ASR-only baseline without any extra cost at inference time, and reductions of 6% and 8% compared to a stronger MUTE-L baseline which trains the decoder with the same text data as our model. We achieve further improvements when we train masked language model on Librispeech data or when we use machine translation as the auxiliary task, without significantly sacrificing performance on the task itself.

Keywords

sequence-to-sequence, multitask, end-to-end ASR, masked language model, machine translation

Authors

YUSUF, B.; GANDHE, A.; SOKOLOV, A.

Released

27. 5. 2022

Publisher

IEEE Signal Processing Society

Location

Singapore

ISBN

978-1-6654-0540-9

Book

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Pages from

8297

Pages to

8301

Pages count

5

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9746554

BibTex

@inproceedings{BUT178379,
  author="Bolaji {Yusuf} and Ankur {Gandhe} and Alex {Sokolov}",
  title="Usted: Improving ASR with a Unified Speech and Text Encoder-Decoder",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2022",
  pages="8297--8301",
  publisher="IEEE Signal Processing Society",
  address="Singapore",
  doi="10.1109/ICASSP43922.2022.9746554",
  isbn="978-1-6654-0540-9",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9746554"
}