DocumentCode :
2391532
Title :
A study of LVQ learning schedules for ANN speaker identification
Author :
Castellano, Rerre
Author_Institution :
Queensland Univ. of Technol., Brisbane, Qld., Australia
fYear :
1994
fDate :
22-26 Aug 1994
Firstpage :
902
Abstract :
Over the past few years, artificial neural networks (ANNs) based on learning vector quantisation (LVQ) algorithms have received considerable attention as pattern classifiers. LVQ2 is currently the preferred choice for automatic speaker identification (ASI) applications. The paper investigates 76 ANN ASI learning schedules incorporating the main LVQ variants, for a 21 speaker text independent database. It concludes that a one stage schedule based on LVQ1 with weak or no repulsion is at least as efficient as more complex LVQ2 schedules
Keywords :
neural nets; pattern matching; speaker recognition; vector quantisation; ANN ASI learning schedules; ANN speaker identification; LVQ learning schedules; LVQ2; artificial neural networks; automatic speaker identification; learning vector quantisation; one stage schedule; pattern classifiers; text independent database; Artificial neural networks; Australia; Databases; Decision making; Feature extraction; Loudspeakers; Pattern matching; Signal processing algorithms; Speech; Student members;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON '94. IEEE Region 10's Ninth Annual International Conference. Theme: Frontiers of Computer Technology. Proceedings of 1994
Print_ISBN :
0-7803-1862-5
Type :
conf
DOI :
10.1109/TENCON.1994.369180
Filename :
369180
Link To Document :
بازگشت