HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Continuous Speech Classification Systems for Voice Pathologies Identification

Abstract : Voice pathologies identification using speech processing methods can be used as a preliminary diagnostic. The aim of this study is to compare the performance of sustained vowel /a/ and continuous speech task in identification systems to diagnose voice pathologies. The system recognizes between three classes consisting of two different pathologies sets and healthy subjects. The signals are evaluated using MFCC (Mel Frequency Cepstral Coefficients) as speech signal features, applied to SVM (Support Vector Machines) and GMM (Gaussian Mixture Models) classifiers. For continuous speech, the GMM system reaches 74% accuracy rate while the SVM system obtains 72% accuracy rate. For the sustained vowel /a/, the accuracy achieved by the GMM and the SVM is 66% and 69% respectively, a lower result than with continuous speech.
Document type :
Conference papers
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download

Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Friday, July 8, 2016 - 2:59:46 PM
Last modification on : Wednesday, November 10, 2021 - 5:26:08 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Hugo Cordeiro, Carlos Meneses, José Fonseca. Continuous Speech Classification Systems for Voice Pathologies Identification. 6th Doctoral Conference on Computing, Electrical and Industrial Systems (DoCEIS), Apr 2015, Costa de Caparica, Portugal. pp.217-224, ⟨10.1007/978-3-319-16766-4_23⟩. ⟨hal-01343485⟩



Record views


Files downloads