Title :
Learning vector quantization in text-independent automatic speaker recognition
Author :
Filho, Thomas E Filgueiras ; Messina, Ronaldo O. ; Cabral, Euvaldo F.
Author_Institution :
Escola Politecnica, Sao Paulo Univ., Brazil
Abstract :
In this paper is reported a comparison among the learning vector quantization (LVQ) and two other common approaches to text-independent speaker recognition, namely Gaussian mixture models (GMM) and vector quantization (VQ). The LVQ method uses neural nets. The results shows that it is less efficient in terms of recognition scores than the GMM
Keywords :
learning (artificial intelligence); neural nets; speaker recognition; vector quantisation; GMM; Gaussian mixture models; LVQ; VQ; learning vector quantization; neural nets; text-independent automatic speaker recognition; Argon; Automatic speech recognition; Electronic learning; Electronic switching systems; Speaker recognition; Speech recognition; Statistical analysis; Testing; Text recognition; Vector quantization;
Conference_Titel :
Neural Networks, 1998. Proceedings. Vth Brazilian Symposium on
Conference_Location :
Belo Horizonte
Print_ISBN :
0-8186-8629-4
DOI :
10.1109/SBRN.1998.731010
