Title :
Speaker segmentation using parallel fusion between three classifiers
Author :
Ouamour, S. ; Sayoud, H. ; Guerti, M.
Author_Institution :
Inst. Electron. & Comput., USTHB Univ., Algiers, Algeria
Abstract :
In this paper, we deal with the problem of speaker segmentation. This speciality consists in splitting the audio document into homogeneous areas. Each area is attributed to one speaker. Speaker segmentation (or speaker change detection) consists in detecting the points where the speaker identity changes, in a multi-speaker audio stream. These points or times are called ¿Break Points¿.
Keywords :
Gaussian processes; neural nets; speaker recognition; support vector machines; audio document; mono-Gaussian statistical measure; multilayer perceptron; parallel fusion; speaker change detection; speaker segmentation; support vector machines; Acoustic measurements; Broadcasting; Circuits and systems; Databases; Loudspeakers; Speech analysis; Speech enhancement; Support vector machine classification; Support vector machines; TV; Fusion; Neural networks; Relativity based classification; SVM; Speaker segmentation;
Conference_Titel :
Signals, Circuits and Systems (SCS), 2009 3rd International Conference on
Conference_Location :
Medenine
Print_ISBN :
978-1-4244-4397-0
Electronic_ISBN :
978-1-4244-4398-7
DOI :
10.1109/ICSCS.2009.5412583
