%0 Conference Proceedings
%T Continuous Speech Classification Systems for Voice Pathologies Identification
%+ Faculdade de Ciências e Tecnologia = School of Science & Technology (FCT NOVA)
%+ High Institute of Engineering of Lisbon
%A Cordeiro, Hugo
%A Meneses, Carlos
%A Fonseca, José
%Z Part 8: Signal Processing in Medicine
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 6th Doctoral Conference on Computing, Electrical and Industrial Systems (DoCEIS)
%C Costa de Caparica, Portugal
%Y Luis M. Camarinha-Matos
%Y Thais A. Baldissera
%Y Giovanni Di Orio
%Y Francisco Marques
%3 Technological Innovation for Cloud-Based Engineering Systems
%V AICT-450
%P 217-224
%8 2015-04-13
%D 2015
%R 10.1007/978-3-319-16766-4_23
%K Voice pathologies identification
%K Continuous speech
%K Gaussian mixture models
%K Support vector machines
%Z Computer Science [cs]Conference papers
%X 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.
%G English
%Z TC 5
%Z WG 5.5
%2 https://inria.hal.science/hal-01343485/document
%2 https://inria.hal.science/hal-01343485/file/336594_1_En_23_Chapter.pdf
%L hal-01343485
%U https://inria.hal.science/hal-01343485
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-WG5-5
%~ IFIP-DOCEIS
%~ IFIP-AICT-450