Title :
Improved MO-LRT VAD based on bispectra Gaussian model
Author :
Górriz, J.M. ; Ramírez, J. ; Segura, J.C. ; Puntonet, C.G.
Author_Institution :
Dpto. de Teoria de la Sehal, Telematica y Communicaciones, Granada, Spain
fDate :
7/21/2005 12:00:00 AM
Abstract :
A robust algorithm for voice activity detection (VAD) is presented. It defines a likelihood ratio test (LRT) involving multiple and independent observations of the bispectra. The proposed VAD provides significant improvements in speech/pause discrimination when compared to standardised and recently reported VADs.
Keywords :
Gaussian distribution; maximum likelihood detection; spectral analysis; speech processing; MO-LRT VAD; bispectra Gaussian model; likelihood ratio test; pause discrimination; speech discrimination; voice activity detection;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20051761
