Robust scoring of voice exercises in computer-based speech therapy systems

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

2 Citations (Scopus)

Abstract

Speech therapy is essential to help children with speech sound disorders. While some computer tools for speech therapy have been proposed, most focus on articulation disorders. Another important aspect of speech therapy is voice quality but not much research has been developed on this issue. As a contribution to fill this gap, we propose a robust scoring model for voice exercises often used in speech therapy sessions, namely the sustained vowel and the increasing/decreasing pitch variation exercises. The models are learned with a support vector machine and double crossvalidation, and obtained accuracies from approximately 73:98% to 85:93% while showing a low rate of false negatives. The learned models allow classifying the children's answers on the exercises, thus providing them with real-time feedback on their performance.

Original languageEnglish
Title of host publication24th European Signal Processing Conference, EUSIPCO 2016
PublisherIEEE
Pages393-397
Number of pages5
ISBN (Electronic)9780992862657
DOIs
Publication statusPublished - 28 Nov 2016
Event24th European Signal Processing Conference, EUSIPCO 2016 - Budapest, Hungary
Duration: 28 Aug 20162 Sep 2016

Publication series

NameEuropean Signal Processing Conference
PublisherIEEE
Volume2016-November
ISSN (Print)2219-5491

Conference

Conference24th European Signal Processing Conference, EUSIPCO 2016
CountryHungary
CityBudapest
Period28/08/162/09/16

Keywords

  • Cross-validation
  • Robust scoring
  • Speech therapy
  • Support vector machines

Fingerprint Dive into the research topics of 'Robust scoring of voice exercises in computer-based speech therapy systems'. Together they form a unique fingerprint.

Cite this