Title :
A V/UV Speech Detection based on Characterization of Background Noise
Author :
Beritelli, Francesco ; Casale, Salvatore ; Russo, Alessandra ; Serrano, Salvatore
Author_Institution :
Dipt. di Ing. Inf. e delle Telecomun., Univ. degli Studi di Catania, Catania, Italy
Abstract :
The paper presents an adaptive system for voiced/unvoiced (V/UV) speech detection in the presence of background noise. Genetic algorithms were used to select the features that offer the best V/UV detection according to the output of a background noise classifier (NC) and a signal to noise ratio estimation (SNRE) system. The system was implemented and the tests performed using the TIMIT speech corpus and its phonetic classification. The results were compared with a non-adaptive classification system and the V/UV detectors adopted by three important speech coding standards: LPC10, ITU-T G.723.1 and ETSI AMR. In all cases the adaptive V/UV classifier outperformed the traditional solutions.
Keywords :
feature extraction; genetic algorithms; speech coding; speech recognition; TIMIT speech corpus; V/UV speech detection; adaptive system; background noise classifier; genetic algorithms; phonetic classification; signal to noise ratio estimation; speech coding standards; unvoiced speech detection; voiced speech detection; Adaptive systems; Background noise; Detectors; Genetic algorithms; Performance evaluation; Signal to noise ratio; Speech coding; Speech enhancement; System testing; Telecommunication standards; V/UV classification; adaptive system; features selection; genetic algorithm;
Conference_Titel :
Signal Processing and Communications, 2007. ICSPC 2007. IEEE International Conference on
Conference_Location :
Dubai
Print_ISBN :
978-1-4244-1235-8
Electronic_ISBN :
978-1-4244-1236-5
DOI :
10.1109/ICSPC.2007.4728295
