Paper Info
Title
Dysphonia Detection Based On Modulation Spectral Features And Cepstral Coefficients
Abstract
In this paper, we combine modulation spectral features with mel-frequency cepstral coefficients for automatic detection of dysphonia. For classification purposes, dimensions of the original modulation spectra are reduced using higher order singular value decomposition (HOSVD). Most relevant features are selected based on their mutual information to discrimination between normophonic and dysphonic speakers made by experts. Features that highly correlate with voice alterations are associated then with a support vector machine (SVM) classifier to provide an automatic decision. Recognition experiments using two different databases suggest that the system provides complementary information to the standard mel-cepstral features.
Year
DOI
Venue
2010
10.1109/ICASSP.2010.5495020
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
Keywords
Field
DocType
pathologic voice detection, modulation spectrum, feature normalization, mutual information, SVD
Mel-frequency cepstrum,Singular value decomposition,Pattern recognition,Computer science,Support vector machine,Feature extraction,Speech recognition,Speaker recognition,Artificial intelligence,Mutual information,Higher-order singular value decomposition,Classifier (linguistics)
Conference
ISSN
Citations 
PageRank 
1520-6149
5
0.49
References 
Authors
0
4
Name
Order
Citations
PageRank
Maria E. Markaki1182.56
Yannis Stylianou21436140.45
Julián D. Arias-Londoño317217.48
Juan Ignacio Godino-Llorente418230.35