12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Automatic Selection of Acoustic and Non-Linear Dynamic Features in Voice Signals for Hypernasality Detection

J. R. Orozco-Arroyave (1), S. Murillo-Rendón (2), A. M. Álvarez-Meza (2), J. D. Arias-Londoño (3), E. Delgado-Trejos (4), J. F. Vargas-Bonilla (1), C. G. Castellanos-Domínguez (2)

(1) Universidad de Antioquia, Colombia
(2) Universidad Nacional de Colombia, Colombia
(3) Universidad Antonio Nariño, Colombia
(4) Instituto Tecnológico Metropolitano, Colombia

Automatic detection of hypernasality in voices of children with Cleft Lip and Palate (CLP) is made considering two characterization techniques, one based on acoustic, noise and cepstral analysis and other based on nonlinear dynamic features. Besides characterization, two automatic feature selection techniques are implemented in order to find optimal sub-spaces to better discriminate between healthy and hypernasal voices. Results indicate that nonlinear dynamic features are valuable tool for automatic detection of hypernasality; additionally both feature selection techniques show stable and consistent results, achieving accuracy levels of up to 93.73%.

Full Paper

Bibliographic reference.  Orozco-Arroyave, J. R. / Murillo-Rendón, S. / Álvarez-Meza, A. M. / Arias-Londoño, J. D. / Delgado-Trejos, E. / Vargas-Bonilla, J. F. / Castellanos-Domínguez, C. G. (2011): "Automatic selection of acoustic and non-linear dynamic features in voice signals for hypernasality detection", In INTERSPEECH-2011, 529-532.