Novel algorithm for speech segregation by optimized k-means of statistical properties of clustered features

Almgotir Kadhim, Hasan, Woo, Wai Lok and Dlay, Satnam (2016) Novel algorithm for speech segregation by optimized k-means of statistical properties of clustered features. In: 2015 IEEE International Conference on Progress in Informatics and Computing (PIC). IEEE, pp. 286-291. ISBN 978-1-4673-8086-7

Full text not available from this repository.

Abstract

To simplify the jobs of speaker diarization and speech separation, at first, speech signal should be segregated to two speech formats, dialog and mixture. This paper describes a new algorithm which achieves that first step efficiently. The algorithm is based on Perceptual Linear Predictive feature extraction, optimized k-means and both top-down & bottom-up scenarios. After extracting features of the observation signal, k-means clusters the statistical properties such as variances of the PDF (histogram) of clustered extracted features. k-means is optimized by discounting the worst pattern of clustering step through doing the k-means procedure twice. The feedback loop is necessary for the guiding of the optimized k-means by exploiting the attributes of ordinary k-means. The results of segregation are excellent. The calculated diarization error rate of outputs is very limited.

Item Type:	Book Section
Uncontrolled Keywords:	speaker diarization, speech segregation, speech separation, k-means, perceptual linear predictive, top-down scenario, bottom-up scenario, clustering, segmentation, dierization error rate
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Becky Skoyles
Date Deposited:	05 Apr 2019 13:21
Last Modified:	10 Oct 2019 20:34
URI:	http://nrl.northumbria.ac.uk/id/eprint/38804

Downloads