Predictive neural networks applied to phoneme recognition

All of RECERCAT

To access the full text documents, please follow this link: http://hdl.handle.net/2117/88538

Title:	Predictive neural networks applied to phoneme recognition
Author:	Freitag, Fèlix; Monte Moreno, Enrique; Salavedra Molí, Josep
Other authors:	Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors; Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions; Universitat Politècnica de Catalunya. CNDS - Xarxes de Computadors i Sistemes Distribuïts; Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
Abstract:	In this paper a phoneme recognition system based on predictive neural networks is proposed. Neural networks are used to predict observation vectors of speech frames. The obtained prediction error is used for phoneme recognition as 1) distortion measure on the frame level and 2) as feature, which is statistically modeled by the Rayleigh distribution. Continuous speech phoneme recognition experiments are performed different settings of the system are evaluated.
Abstract:	Peer Reviewed
Subject(s):	-Àrees temàtiques de la UPC::Enginyeria de la telecomunicació -Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic -Speech processing systems -Processament de la parla
Rights:	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
Document type:	Article - Published version Conference Object
Share: