Dysfluency Classification in Speech Using a Biological Sound Perception Model

Melanie Jouaiti, Kerstin Dautenhahn

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

Abstract

Dysfluency classification for stuttered speech has been tackled from different perspectives over the years, with research being more and more focused on deep learning. Here, we use a specific biological model of sound texture perception to extract a subband representation of speech and statistical features. A statistical analysis was also performed to identify relevant features. Afterwards, dysfluency classification was performed using a Random Forest Classifier to perform multi-label classification on the FluencyBank dataset and Support Vector Machine on the UCLASS dataset. This method performs as well or better than current state of the art deep learning algorithm, suggesting that approaching speech classification problems from a more biological point of view is a promising direction.
Original languageEnglish
Title of host publication2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)
PublisherIEEE
Pages173-177
Number of pages5
ISBN (Electronic)9798350320886, 9798350320879
ISBN (Print)9798350320893
DOIs
Publication statusPublished - 21 Mar 2023
Event2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI) - Toronto, ON, Canada
Duration: 26 Nov 202227 Nov 2022

Publication series

NameInternational Conference on Soft Computing and Machine Intelligence (ISCMI)
PublisherIEEE
ISSN (Print)2640-0154
ISSN (Electronic)2640-0146

Conference

Conference2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)
Period26/11/2227/11/22

Bibliographical note

Presented 27 Nov 2022 at the 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)

Keywords

  • Support vector machines
  • Deep learning
  • Statistical analysis
  • Biological system modeling
  • Computational modeling
  • Feature extraction
  • Real-time systems

Fingerprint

Dive into the research topics of 'Dysfluency Classification in Speech Using a Biological Sound Perception Model'. Together they form a unique fingerprint.

Cite this