Improved mask-ctc for non-autoregressive end-to-end asr

Yosuke Higuchi, Hirofumi Inaguma, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi

Research output: Contribution to journalConference articlepeer-review

Abstract

For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. The recently proposed end-to-end ASR system based on mask-predict with connectionist temporal classification (CTC), Mask-CTC, fulfills this demand by generating tokens in a non-autoregressive fashion. While Mask- CTC achieves remarkably fast inference speed, its recognition performance falls behind that of conventional autoregressive (AR) systems. To boost the performance of Mask-CTC, we first propose to enhance the encoder network architecture by employing a recently proposed architecture called Conformer. Next, we propose new training and decoding methods by introducing auxiliary objective to predict the length of a partial target sequence, which allows the model to delete or insert tokens during inference. Experimental results on different ASR tasks show that the proposed approaches improve Mask-CTC significantly, outperforming a standard CTC model (15.5%!9.1% WER on WSJ). Moreover, Mask- CTC now achieves competitive results to AR models with no degradation of inference speed (< 0.1 RTF using CPU). We also show a potential application of Mask-CTC to end-to-end speech translation.

Original languageEnglish
Pages (from-to)8363-8367
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 2021 Jun 62021 Jun 11

Keywords

  • Connectionist temporal classification
  • End-to-end speech recognition
  • End-to-end speech translation
  • Non-autoregressive sequence generation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Improved mask-ctc for non-autoregressive end-to-end asr'. Together they form a unique fingerprint.

Cite this