Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/44024
Title: Voice pathology detection in continuous speech using nonlinear dynamics
Authors: Orozco, Juan R.
Vargas, Jesus F.
Alonso, Jesus B. 
Ferrer, Miguel A. 
Travieso, Carlos M. 
Henríquez, P. 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Pathology , Speech , Complexity theory , Accuracy , Correlation , Estimation , Acoustics
Issue Date: 2012
Journal: 2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012
Conference: 2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012 
Abstract: A novel methodology, based on the estimation of nonlinear dynamics features, is presented for automatic detection of pathologies in the phonatory system considering continuous speech records (text-dependent). The proposed automatic segmentation and characterization of the voice registers does not require the estimation of the pitch period, therefore it doesn't depend on the gender and intonation of the patients. A robust methodology for finding the features that better discriminate between healthy and pathological voices and also for analyzing the affinity among them is also presented. An average success rate of 95% ± 3.54% in the automatic detection of voice pathologies is achieved considering only six features. The results indicate that nonlinear dynamics is a good alternative for automatic detection of abnormal phonations in continuous speech.
URI: http://hdl.handle.net/10553/44024
ISBN: 9781467303828
DOI: 10.1109/ISSPA.2012.6310440
Source: 2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012 (6310440), p. 1030-1033
Appears in Collections:Actas de congresos
Show full item record

SCOPUSTM   
Citations

10
checked on Feb 21, 2021

Page view(s)

18
checked on Feb 22, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.