Enhancement of a text-independent speaker verification system by using feature combination and parallel structure classifiers

e-Archivo Repository

Show simple item record

dc.contributor.author Abdalmalak Dawoud, Kerlos Atia
dc.contributor.author Gallardo Antolín, Ascensión
dc.date.accessioned 2020-11-30T12:13:52Z
dc.date.available 2020-11-30T12:13:52Z
dc.date.issued 2018-02-01
dc.identifier.bibliographicCitation Abdalmalak, K.A., Gallardo-Antolín, A. Enhancement of a text-independent speaker verification system by using feature combination and parallel structure classifiers. Neural Comput & Applic 29, 637–651 (2018)
dc.identifier.issn 0941-0643
dc.identifier.uri http://hdl.handle.net/10016/31500
dc.description.abstract Speaker verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under noisy conditions. On the one hand, the choice of the most appropriate acoustic features is a crucial factor for performing robust speaker verification. The acoustic parameters used in the proposed system are: Mel Frequency Cepstral Coefficients, their first and second derivatives (Deltas and Delta-Deltas), Bark Frequency Cepstral Coefficients, Perceptual Linear Predictive, and Relative Spectral Transform Perceptual Linear Predictive. In this paper, a complete comparison of different combinations of the previous features is discussed. On the other hand, the major weakness of a conventional support vector machine (SVM) classifier is the use of generic traditional kernel functions to compute the distances among data points. However, the kernel function of an SVM has great influence on its performance. In this work, we propose the combination of two SVM-based classifiers with different kernel functions: linear kernel and Gaussian radial basis function kernel with a logistic regression classifier. The combination is carried out by means of a parallel structure approach, in which different voting rules to take the final decision are considered. Results show that significant improvement in the performance of the SV system is achieved by using the combined features with the combined classifiers either with clean speech or in the presence of noise. Finally, to enhance the system more in noisy environments, the inclusion of the multiband noise removal technique as a preprocessing stage is proposed.
dc.description.sponsorship The authors want to thank Erasmus Mundus 3Green-IT ́ program for its grant for providing the funding for this work. This work has also been partially supported by the Spanish Government Grant TEC2014-53390-P and by the Regional Government of Madrid S2013/ICE-2845-CASI-CAM±CM project.
dc.language.iso eng
dc.publisher Springer
dc.rights © The Natural Computing Applications Forum 2016
dc.subject.other Speaker verification
dc.subject.other Speech feature extraction
dc.subject.other MFCC
dc.subject.other BFCC
dc.subject.other PLP
dc.subject.other RASTA-PLP
dc.subject.other SVM
dc.subject.other Logistic regression
dc.subject.other Feature combination
dc.subject.other Classifier combination
dc.title Enhancement of a text-independent speaker verification system by using feature combination and parallel structure classifiers
dc.type article
dc.subject.eciencia Ingeniería Mecánica
dc.identifier.doi https://doi.org/10.1007/s00521-016-2470-x
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. TEC2014-53390-P
dc.relation.projectID Comunidad de Madrid. S2013/ICE-2845-CASI-CAM±CM
dc.type.version acceptedVersion
dc.identifier.publicationfirstpage 637
dc.identifier.publicationissue 3
dc.identifier.publicationlastpage 651
dc.identifier.publicationtitle Neural Computing & Applications
dc.identifier.publicationvolume 29
dc.identifier.uxxi AR/0000020971
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.contributor.funder Comunidad de Madrid
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record