IEICE TRANSACTIONS on Information
Comparative Study of Speaker Identification Methods: dPLRM, SVM and GMM
Summary :
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].
- Publication
- IEICE TRANSACTIONS on Information Vol.E89-D No.3 pp.1066-1073
- Publication Date
- 2006/03/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e89-d.3.1066
- Type of Manuscript
- Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
- Category
- Speaker Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Tomoko MATSUI, Kunio TANABE, "Comparative Study of Speaker Identification Methods: dPLRM, SVM and GMM" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 3, pp. 1066-1073, March 2006, doi: 10.1093/ietisy/e89-d.3.1066.
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].
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.1066/_p
Copy
@ARTICLE{e89-d_3_1066,
author={Tomoko MATSUI, Kunio TANABE, },
journal={IEICE TRANSACTIONS on Information},
title={Comparative Study of Speaker Identification Methods: dPLRM, SVM and GMM},
year={2006},
volume={E89-D},
number={3},
pages={1066-1073},
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].},
keywords={},
doi={10.1093/ietisy/e89-d.3.1066},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Comparative Study of Speaker Identification Methods: dPLRM, SVM and GMM
T2 - IEICE TRANSACTIONS on Information
SP - 1066
EP - 1073
AU - Tomoko MATSUI
AU - Kunio TANABE
PY - 2006
DO - 10.1093/ietisy/e89-d.3.1066
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - 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].
ER -
English
