Speaker diary compilation by dependent combination of audio coefficients

Kadhim, Hasan Almgotir, Woo, Wai Lok and Dlay, Satnam (2016) Speaker diary compilation by dependent combination of audio coefficients. International Journal of Simulation: Systems, Science and Technology, 17 (34). ISSN 1473-8031

Full text not available from this repository.

Abstract

The paper describes a novel method that improvises the procedure for supervised speaker diary compilation. The procedure supposes that the database of the speakers is available. Initially, the database and observation signal of the speakers, are prepared. The audio features have been extracted from the database and the observation signal. Instead of using one of Mel Frequency Cepstral Coefficient, Perceptual Linear Prediction, or Power Normalized Cepstral Coefficients, a combination of all of them have been used. The combination form of these features is independent, i.e. they are concatenated in the feature matrix. The comparison between features of observation signal and statistical properties of database features, has been made. A comparing procedure is used to make the decision of the logical mask for comparison. Both of bottom-up and top-down scenarios collaborate to complete the last decisions successfully. Diary compilation Error Rate test denotes that combination of features has less errors than any one alone.

Item Type:	Article
Uncontrolled Keywords:	Clustering, Mel Feature Cepstral Coefficient, Perceptual Linear Predictive, Power Normalized Cepstral Coefficient, Segmentation, Speaker diary compilation
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	09 Apr 2019 11:45
Last Modified:	10 Oct 2019 20:16
URI:	http://nrl.northumbria.ac.uk/id/eprint/38861

Downloads