COMBINING NOVEL ACOUSTIC FEATURES USING SVM TO DETECT SPEAKER CHANGING POINTS

Haishan Zhong, David Cho, Vladimir Pervouchine, Graham Leedham

2008

Abstract

Automatic speaker change point detection separates different speakers from continuous speech signal by utilising the speaker characteristics. It is often a necessary step before using a speaker recognition system. Acoustic features of the speech signal such as Mel Frequency Cepstral Coefficients (MFCC) and Linear Prediction Cepstral Coefficients (LPCC) are commonly used to represent a speaker. However, the features are affected by speech content, environment, type of recording device, etc. So far, no features have been discovered, which values depend only on the speaker. In this paper four novel feature types proposed in recent journals and conference papers for speaker verification problem, are applied to the problem of speaker change point detection. The features are also used to form a combination scheme using an SVM classifier. The results shows that the proposed scheme improves the performance of speaker changing point detection as compared to the system that uses MFCC features only. Some of the novel features of low dimensionality give comparable speaker change point detection accuracy to the high-dimensional MFCC features.

Paper Citation

in Harvard Style

Zhong H., Cho D., Pervouchine V. and Leedham G. (2008). COMBINING NOVEL ACOUSTIC FEATURES USING SVM TO DETECT SPEAKER CHANGING POINTS . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 224-227. DOI: 10.5220/0001060402240227

in Bibtex Style

@conference{biosignals08,
author={Haishan Zhong and David Cho and Vladimir Pervouchine and Graham Leedham},
title={COMBINING NOVEL ACOUSTIC FEATURES USING SVM TO DETECT SPEAKER CHANGING POINTS},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={224-227},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001060402240227},
isbn={978-989-8111-18-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008)
TI - COMBINING NOVEL ACOUSTIC FEATURES USING SVM TO DETECT SPEAKER CHANGING POINTS
SN - 978-989-8111-18-0
AU - Zhong H.
AU - Cho D.
AU - Pervouchine V.
AU - Leedham G.
PY - 2008
SP - 224
EP - 227
DO - 10.5220/0001060402240227