Skip to main navigation Skip to search Skip to main content

CAD of sigmatism using neural networks

  • Purdue University
  • Jesuit University Ignatianum in Krakow

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

4 Citations (Scopus)

Abstract

Sigmatism, or lisp, is a common speech pathology defined by the misarticulation of sibilants and commonly appears in preschool-age children. Automated diagnosis from speech data has been used for other disorders, and the use of acoustic features could objectify the diagnosis procedure. 1593 multichannel recordings from 85 young children were subjected to feature extraction and classification using a neural network. The classification performance was evaluated for single and multichannel input as well as multiple feature sets and articulation phases. Multichannel recordings increased the classifier accuracy from 78.75% to 87.27% when using cepstral and spectral features. The introduction of a multichannel acoustic features was shown to increase sigmatism detection accuracy.

Original languageEnglish
Title of host publicationInformation Technology in Biomedicine - Proceedings 6th International Conference, ITIB’2018
EditorsEwa Pietka, Pawel Badura, Jacek Kawa, Wojciech Wieclawek
PublisherSpringer Verlag
Pages260-271
Number of pages12
ISBN (Print)9783319912103
DOIs
Publication statusPublished - 2019
Event6th International Conference on Information Technology in Biomedicine, ITIB 2018 - Kamien Slaski, Poland
Duration: 18 Jun 201820 Jun 2018

Publication series

NameAdvances in Intelligent Systems and Computing
Volume762
ISSN (Print)2194-5357

Conference

Conference6th International Conference on Information Technology in Biomedicine, ITIB 2018
Country/TerritoryPoland
CityKamien Slaski
Period18/06/1820/06/18

Keywords

  • ANNs
  • Computer-aided pronunciation evaluation
  • Multichannel signal processing
  • Sibilants
  • Sigmatism diagnosis

ASJC Scopus subject areas

  • Control and Systems Engineering
  • General Computer Science

Fingerprint

Dive into the research topics of 'CAD of sigmatism using neural networks'. Together they form a unique fingerprint.

Cite this