Robust text-independent speaker identification using hybrid PCA&LDA

Authors:
Min-Seok Kim;Ha-Jin Yu;Keun-Chang Kwak;Su-Young Chi
Affiliations:
School of Computer Science, University of Seoul, Seoul, Korea;School of Computer Science, University of Seoul, Seoul, Korea;Human-Robot Interaction Research Team, Intelligent Robot Research Division, Electronics and Telecommunication Research Institute (ETRI), Korea;Human-Robot Interaction Research Team, Intelligent Robot Research Division, Electronics and Telecommunication Research Institute (ETRI), Korea
Venue:
MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Year:
2006

Citing 5
Cited 0

Spoken Language Processing: A Guide to Theory, Algorithm, and System Development

Spoken Language Processing: A Guide to Theory, Algorithm, and System Development
Acoustical and Environmental Robustness in Automatic Speech Recognition

Acoustical and Environmental Robustness in Automatic Speech Recognition
Discriminant Analysis of Principal Components for Face Recognition

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
A comparison of composite features under degraded speech in speaker recognition

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have been building a text-independent speaker recognition system in noisy conditions. In this paper, we propose a novel feature using hybrid PCA/LDA. The feature is created from the convectional MFCC(mel-frequency cepstral coefficients) by transforming them using a matrix. The matrix consists of some components from the PCA and LDA transformation matrices. We tested the new feature using Aurora project Database 2 which is intended for the evaluation of algorithms for front-end feature extraction algorithms in background noise. The proposed method outperformed in all noise types and noise levels. It reduced the relative recognition error by 63.6% than using the baseline feature when the SNR is 15dB.