DocumentCode
2208038
Title
Using neural networks for automatic speaker recognition: a practical approach
Author
Pinto, Rafael G C P ; Pinto, Hardy L C P ; Calôba, Luiz P.
Author_Institution
COPPE-UFRJ, Rio de Janeiro, Brazil
Volume
2
fYear
1995
fDate
13-16 Aug 1995
Firstpage
1078
Abstract
This paper describes an automatic speaker recognition method for telephone speech, using acoustic processing of a single trisyllabic Portuguese word. Cepstrum coefficients are extracted from the linear predictive coefficients and no further processing is needed. In this method, the traditional classification method (non-Euclidean distance measurement) was efficiently substituted by a multi-layer neural network with encouraging results
Keywords
cepstral analysis; linear predictive coding; neural nets; speaker recognition; speech processing; Portuguese word; acoustic processing; automatic speaker recognition; cepstrum coefficients; classification; linear predictive coefficients; multilayer neural network; telephone speech; Bandwidth; Cepstrum; Communication system security; Digital filters; Finite impulse response filter; Neural networks; Speaker recognition; Spectrogram; Speech recognition; Telephony;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1995., Proceedings., Proceedings of the 38th Midwest Symposium on
Conference_Location
Rio de Janeiro
Print_ISBN
0-7803-2972-4
Type
conf
DOI
10.1109/MWSCAS.1995.510281
Filename
510281
Link To Document