ITRW on Non-Linear Speech Processing (NOLISP 05) Barcelona, Spain April 19-22, 2005

Discriminative methods for the detection of voice disorders

Juan Ignacio Godino-Llorente (1), Pedro Gómez-Vilda (1), Nicolás Sáenz-Lechón (1), Manuel Blanco-Velasco (2), Fernando Cruz-Roldán (2), Miguel Angel Ferrer (3)

(1) Universidad Politécnica de Madrid, EUIT de Telecomunicación, Ctra. de Valencia, Madrid, Spain
(2) Universidad de Alcalá, Escuela Politécnica, Alcalá de Henares, Madrid, Spain
(3) Universidad de Las Palmas de Gran Canaria, ETSI de Telecomunicación, Las Palmas de Gran Canaria, Spain

Support Vector Machines (SVMs) have become a popular tool for discriminative classification. An exciting area of recent application of SVMs is in speech processing. In this paper discriminatively trained SVMs have been in-troduced as a novel approach for the automatic detection of voice impairments. SVMs have a distinctly different modelling strategy in the detection of voice impairments problem, compared to other methods found in the literature (such a Gaussian Mixture or Hidden Markov Models): the SVM models the boundary between the classes instead of modelling the probability density of each class. In this paper it is shown that the scheme proposed fed with short-term cepstral and noise parameters can be applied for the detection of voice impairments with a good performance.

Full Paper

Bibliographic reference.  Godino-Llorente, Juan Ignacio / Gómez-Vilda, Pedro / Sáenz-Lechón, Nicolás / Blanco-Velasco, Manuel / Cruz-Roldán, Fernando / Ferrer, Miguel Angel (2005): "Discriminative methods for the detection of voice disorders", In NOLISP-2005, 158-167.