Dysfluency Classification in Stuttered Speech Using Deep Learning for Real-Time Applications

Melanie Jouaiti, Kerstin Dautenhahn

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

Abstract

Stuttering detection and classification are important issues in speech therapy as they could help therapists track the progression of patients’ dysfluencies. This is also an important tool for technology-assisted speech therapy. In this paper, we combine MFCC and phoneme probabilities to train a neural network for stuttering detection and classification of four dysfluency types. We evaluate our system on the UCLASS, FluencyBank and SEP-28K datasets and show that our system is effective and suitable for real-time applications.
Original languageEnglish
Title of host publicationICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages6482-6486
Number of pages5
ISBN (Electronic)9781665405409
ISBN (Print)9781665405416
DOIs
Publication statusPublished - 27 Apr 2022
EventICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Singapore, Singapore
Duration: 23 May 202227 May 2022

Publication series

NameInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP)
PublisherIEEE
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

ConferenceICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Period23/05/2227/05/22

Bibliographical note

Presented 27 May 2022, at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Keywords

  • Deep learning
  • Conferences
  • Neural networks
  • Medical treatment
  • Signal processing
  • Real-time systems
  • Acoustics

Fingerprint

Dive into the research topics of 'Dysfluency Classification in Stuttered Speech Using Deep Learning for Real-Time Applications'. Together they form a unique fingerprint.

Cite this