A sequential contrastive learning framework for robust dysarthric speech recognition

  • Lidan Wu
  • , Daoming Zong
  • , Shiliang Sun
  • , Jing Zhao*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

Dysarthria is a manifestation of disruption in the neuromuscular physiology resulting in uneven, slow, slurred, harsh, or quiet speech. Despite the remarkable progress of automatic speech recognition (ASR), it poses great challenges in developing stable ASR for dysarthric individuals due to the high intra- and inter-speaker variations and data deficiency. In this paper, we propose a contrastive learning framework for robust dysarthric speech recognition (DSR) by capturing the dysarthric speech variability. Several speech data augmentation strategies are explored to form two branches of the framework, meanwhile alleviating the scarcity of dysarthria data. We also develop an efficient projection head acting on a sequence of learned hidden representations for defining contrastive loss. Experiment results on DSR demonstrate that the model is better than or comparable to the supervised baseline.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7303-7307
Number of pages5
ISBN (Electronic)9781728176055
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June
ISSN (Print)1520-6149

Conference

Conference2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Country/TerritoryCanada
CityVirtual, Toronto
Period6/06/2111/06/21

Keywords

  • Contrastive learning
  • Data augmentation
  • Dysarthric speech recognition
  • Self-supervised learning

Fingerprint

Dive into the research topics of 'A sequential contrastive learning framework for robust dysarthric speech recognition'. Together they form a unique fingerprint.

Cite this