Speaker Identification on Various Environments Using an Ensemble of Kernel Principal Component Analysis

Il-Ho Yang; Min-Seok Kim; Byung-Min So; Myung-Jae Kim; Ha-Jin Yu

doi:None

All Issue

2012 Vol.31, Issue 3 Preview Page Next Page

Speaker Identification on Various Environments Using an Ensemble of Kernel Principal Component Analysis 커널 주성분 분석의 앙상블을 이용한 다양한 환경에서의 화자 식별

30 April 2012. pp. 188-196

PDF XML

Abstract

In this paper, we propose a new approach to speaker identification technique which uses an ensemble of multiple classifiers (speaker identifiers). KPCA (kernel principal component analysis) enhances features for each classifier. To reduce the processing time and memory requirements, we select limited number of samples randomly which are used as estimation set for each KPCA basis. The experimental result shows that the proposed approach gives a higher identification accuracy than GKPCA (greedy kernel principal component analysis).

Keywords

Speaker identification

Classifier ensemble

PCA

KPCA

GKPCA

본 논문에서는 커널 주성분 분석 (KPCA, kernel principal component analysis)으로 강화한 화자 특징을 이용하여 복수의 분류기를 학습하고 이를 앙상블 결합하는 화자 식별 방법을 제안한다. 이 때, 계산량과 메모리 요구량을 줄이기 위해 전체 화자 특징 벡터 중 일부를 랜덤 선택하여 커널 주성분 분석의 기저를 추정한다. 실험 결과, 제안한 방법이 그리디 커널 주성분 분석 (GKPCA, greedy kernel principal component analysis)보다 높은 화자 식별률을 보였다.

키워드

화자식별

분류기 앙상블

주성분 분석

커널 주성분 분석

그리디 커널 주성분 분석

References

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, John Wiley & Sons, 2001.

B. Scholkopf, A. Smola, K-R. Muller, "Kernel Principal Component Analysis," in Proceedings of International Conference on Artificial Neural Networks, pp. 583- 588, 1997.

10.1007/BFb0020217

J. Shawe-Taylor, and N. Cristianini, Kernel Methods for Pattern Analysis, Cambridge University Press, 2004.

10.1017/CBO978051180968215516276

김민석, 양일호, 유하진, "Greedy Kernel PCA를 이용한 화자식별", 말소리, 66호, 105-116쪽, 2008.

R. Polikar, "Ensemble based Systems in Decision Making," Circuits and Systems Magazine, 2006.

10.1109/MCAS.2006.1688199

D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, "Speaker Verification Using Adapted Gaussian Mixture Models," Digital Signal Processing, Vol. 10, pp. 19- 41, 2000.

10.1006/dspr.1999.0361

D. A. Reynolds and R. C. Rose, "Robust text- independent speaker identification using Gaussian mixture speaker models," IEEE Transactions on Speech Audio Processing, Vol. 3, No. 1, pp. 72-83, 1995.

10.1109/89.365379

H.-G. Hirsch and D. Pearce, "The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in ASR 2000, pp. 181-188, 2000.

H.-G. Hirsch, Fant-fltering and noise adding tool, http://dnt.kr.hs-niederrhein.de/download.html.

Information

Publisher :The Acoustical Society of Korea
Publisher(Ko) :한국음향학회
Journal Title :The Journal of the Acoustical Society of Korea
Journal Title(Ko) :한국음향학회지
Volume : 31
No :3
Pages :188-196
Received Date : 2011-12-08
Revised Date : 2012-01-17
Accepted Date : 2012-03-21

The Journal of the Acoustical Society of KoreaISSN:1225-4428(Print) 2287-3775(Online)한국음향학회

All Issue