Robust phoneme recognition for a speech therapy environment

Sofia Cavaco, João Magalhães, André Grossinho, Isabel Guimarães

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

21 Citations (Scopus)

Abstract

Traditional speech therapy approaches for speech sound disorders have a lot of advantages to gain from computer-based therapy systems. In this paper, we propose a robust phoneme recognition solution for an interactive environment for speech therapy. With speech recognition techniques the motivation elements of computer-based therapy systems can be automated in order to get an interactive environment that motivates the therapy attendee towards better performances. The contribution of this paper is a robust phoneme recognition to control the feedback provided to the patient during a speech therapy session. We compare the results of hierarchical and flat classification, with naive Bayes, support vector machines and kernel density estimation on linear predictive coding coefficients and Mel-frequency cepstral coefficients.
Original languageEnglish
Title of host publicationProceedings of IEEE International Conference on Serious Games and Applications for Health (SeGAH)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Publication statusPublished - 2016
Event2016 IEEE International Conference on Serious Games and Applications for Health (SeGAH) - Orlando University Central Florida, Florida
Duration: 11 May 201613 May 2016

Publication series

Name IEEE International Conference on Serious Games and Applications for Health
PublisherIEEE
ISSN (Electronic)2330-5649

Conference

Conference2016 IEEE International Conference on Serious Games and Applications for Health (SeGAH)
CityFlorida
Period11/05/1613/05/16

Keywords

  • Speech Therapy
  • Phoneme Detection
  • Kernel Density Estimation
  • Naive Bayes
  • Support Vector Machines

Fingerprint

Dive into the research topics of 'Robust phoneme recognition for a speech therapy environment'. Together they form a unique fingerprint.

Cite this