Speaker identification using vector quantization

Article type: Research Article

Authors: Lipeika, Antanas | Lipeikienė, Joana

Affiliations: Institute of Mathematics and Informatics, 2600 Vilnius, Akademijos St. 4, Lithuania

Abstract: The use of vector quantization for speaker identification is investigated. This method differs from the known methods in that the number of centroids is not doubled but increases by 1 at every step. This enables us to obtain identification results at any number of centroids. This method is compared experimentally with the method (Lipeika and Lipeikienė, 1993a, 1993b), where feature vectors of investigative and comparative speakers are compared directly.

Keywords: speaker identification, likelihood ratio distance, vector quantization

DOI: 10.3233/INF-1995-6202

Journal: Informatica, vol. 6, no. 2, pp. 167-180, 1995