End-to-End Automatic Speech Recognition Integrated with CTC-Based Voice Activity Detection

Takenori Yoshimura, Tomoki Hayashi, Kazuya Takeda, Shinji Watanabe

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

22 Citations (Scopus)

Abstract

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification (CTC) and its extension of CTC/attention architectures. As opposed to an attention-based architecture, input-synchronous label prediction can be performed based on a greedy search with the CTC (pre-)softmax output. This prediction includes consecutive long blank labels, which can be regarded as a non-speech region. We use the labels as a cue for detecting speech segments with simple thresholding. The threshold value is directly related to the length of a non-speech region, which is more intuitive and easier to control than conventional VAD hyperparameters. Experimental results on unsegmented data show that the proposed method outperformed the baseline methods using the conventional energy-based and neural-network-based VAD methods and achieved an RTF less than 0.2. The proposed method is publicly available.1

Original languageEnglish
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6999-7003
Number of pages5
ISBN (Electronic)9781509066315
DOIs
Publication statusPublished - 2020 May
Externally publishedYes
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: 2020 May 42020 May 8

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Country/TerritorySpain
CityBarcelona
Period20/5/420/5/8

Keywords

  • CTC greedy search
  • Speech recognition
  • end-to-end
  • streaming
  • voice activity detection

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'End-to-End Automatic Speech Recognition Integrated with CTC-Based Voice Activity Detection'. Together they form a unique fingerprint.

Cite this