Comparative Study of Speaker Identification Methods: dPLRM, SVM and GMM

Authors:
Tomoko Matsui;Kunio Tanabe
Affiliations:
The author is with Institute of Statistical Mathematics, Tokyo, 106--8569 Japan. E-mail: tmatsui@ism.ac.jp,;The author is with Waseda University, Tokyo, 169--0072 Japan.
Venue:
IEICE - Transactions on Information and Systems
Year:
2006

Citing 0
Cited 4

Dynamic spectrum classification by kernel classifiers with divergence-based kernels and its applications to acoustic signals

International Journal of Knowledge Engineering and Soft Data Paradigms
Daily sound recognition using pitch-cluster-maps for mobile robot audition

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Semi-supervised speaker identification under covariate shift

Signal Processing
On the use of perceptual Line Spectral pairs Frequencies and higher-order residual moments for Speaker Identification

International Journal of Biometrics

Quantified Score

Hi-index	0.00

Visualization

Abstract

A comparison of performances is made of three text-independent speaker identification methods based on dual Penalized Logistic Regression Machine (dPLRM), Support Vector Machine (SVM) and Gaussian Mixture Model (GMM) with experiments by 10 male speakers. The methods are compared for the speech data which were collected over the period of 13 months in 6 utterance-sessions of which the earlier 3 sessions were for obtaining training data of 12 seconds' utterances. Comparisons are made with the Mel-frequency cepstrum (MFC) data versus the log-power spectrum data and also with training data in a single session versus in plural ones. It is shown that dPLRM with the log-power spectrum data is competitive with SVM and GMM methods with MFC data, when trained for the combined data collected in the earlier three sessions. dPLRM outperforms GMM method especially as the amount of training data becomes smaller. Some of these findings have been already reported in [1]--[3].