Automatic Selection of Acoustic and Non-Linear Dynamic Features in Voice Signals for Hypernasality Detection.
Juan Rafael Orozco‐Arroyave, Santiago Murillo Rendón, Andrés Marino Álvarez-Meza, Julián D. Arias-Londoño, Edilson Delgado‐Trejos, J. F. Vargas‐Bonilla, German Castellanos-Dominguez · 2011
Automatic detection of hypernasality in voices of children with Cleft Lip and Palate (CLP) is made considering two charca-terization techniques, one based on acoustic, noise and cep-stral analysis and other based on nonlinear dynamic features. Besides characterization, two automatic feature selection tech-niques 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; addtionally both feature selection techniques show stable and consistent results, achieving accuracy levels of up to 93.73%.