Title: Prosodic features-based speaker verification using speaker-specific-text for short utterances

Authors: Jianwu Zhang; Jianchao He; Zhendong Wu; Freeha Azmat; Ping Li

Addresses: School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang, China ' School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang, China ' School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang, China ' School of Engineering, University of Warwick, Coventry CV4 7AL, UK ' School of Mathematics and Computational Science, Sun Yatsen University, Guangzhou, China

Abstract: Over the past several years, Gaussian mixture model and its variants have been dominant architectures in text-independent and text-dependent speaker recognition field. The recognition accuracy of above-mentioned models declines when experimental utterances' length becomes short in practical application. Presently, Mel-frequency cepstral coefficients are generally used to characterise the properties of the vocal tract and widely applied in speech recognition. In addition, prosodic features, such as pitch and formant, are generally considered to describe the glottal characteristics. However, the efficiency of those approaches remains unsatisfactory. In text-dependent short utterance speaker verification systems, prosodic features can assist to improve the recognition result theoretically. In order to optimise the performance of speaker verification systems under the framework of adapted GMM-UBM, we adopt a variant speaker verification system based on prosodic features, in which a dual judgement mechanism is used in order to integrate vocal tract features with prosodic features. Experimental results showed that the new speech recognition system gives a better consequence.

Keywords: speaker verification; text dependent; prosodic features; dual judgement mechanism.

DOI: 10.1504/IJES.2017.084693

International Journal of Embedded Systems, 2017 Vol.9 No.3, pp.250 - 261

Received: 01 Dec 2015
Accepted: 21 Apr 2016
Published online: 21 Jun 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article