A discriminative training algorithm for VQ-based speaker identification

Author

He, Jialong ; Liu, Li ; Palm, Gunther

Author_Institution

Abteilung Neuroinf., Ulm Univ., Germany

Volume

7

Issue

3

fYear

1999

fDate

5/1/1999 12:00:00 AM

Firstpage

353

Lastpage

356

Abstract

A novel method, referred to as group vector quantization (GVQ), is proposed to train VQ codebooks for closed-set speaker identification. In GVQ training, speaker codebooks are optimized for vector groups rather than for individual vectors. An evaluation experiment has been conducted to compare the codebooks trained by the Linde-Buzo-Grey (LBG), the learning vector quantization (LVQ), and the GVQ algorithms. It is shown that the frame scores from the GVQ trained codebooks are less correlated, therefore, the sentence level speaker identification rate increases more quickly with the length of test sentences

Keywords

learning (artificial intelligence); speaker recognition; speech coding; vector quantisation; GVQ algorithm; LBG algorithm; LVQ algorithm; Linde-Buzo-Grey algorithm; VQ codebooks; VQ-based speaker identification; closed-set speaker identification; discriminative training algorithm; frame scores; group vector quantization; learning vector quantization algorithm; sentence level speaker identification rate; speaker codebooks; Density functional theory; Error analysis; Helium; Neural networks; Prototypes; Speaker recognition; Speech; Testing; Training data; Vector quantization;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.759047

Filename

759047