RUN-AND-BACK STITCH SEARCH: NOVEL BLOCK SYNCHRONOUS DECODING FOR STREAMING ENCODER-DECODER ASR

Emiru Tsunoo*, Chaitanya Narisetty, Michael Hentschel, Yosuke Kashiwagi, Shinji Watanabe

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A streaming style inference of encoder-decoder automatic speech recognition (ASR) systems is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding algorithm with a hybrid approach that combines endpoint prediction and endpoint post-determination. In the endpoint prediction, we compute the expectation of the number of tokens that are yet to be emitted in the encoder features of the current blocks using the CTC posterior. Based on the expectation value, the decoder predicts the endpoint to realize continuous block synchronization, as a running stitch. Meanwhile, endpoint post-determination probabilistically detects backward jump of the source-target attention, which is caused by the misprediction of endpoints. Then it resumes decoding by discarding those hypotheses, as back stitch. We combine these methods into a hybrid approach, namely run-and-back stitch search, which reduces the computational cost and latency. Evaluations of various ASR tasks show the efficiency of our proposed decoding algorithm, which achieves a latency reduction, for instance in the Librispeech test set from 1487 ms to 821 ms at the 90th percentile, while maintaining a high recognition accuracy.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7912-7916
Number of pages5
ISBN (Electronic)9781665405409
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: 2022 May 232022 May 27

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period22/5/2322/5/27

Keywords

  • CTC
  • encoder-decoder
  • end-to-end
  • Streaming automatic speech recognition (ASR)
  • Transformer

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'RUN-AND-BACK STITCH SEARCH: NOVEL BLOCK SYNCHRONOUS DECODING FOR STREAMING ENCODER-DECODER ASR'. Together they form a unique fingerprint.

Cite this