dc.contributor.author | Pillay, Surosh | |
dc.contributor.author | Ariyaeeinia, A. | |
dc.contributor.author | Sivakumaran, P. | |
dc.contributor.author | Pawlewski, M. | |
dc.date.accessioned | 2012-12-18T13:59:39Z | |
dc.date.available | 2012-12-18T13:59:39Z | |
dc.date.issued | 2012-06 | |
dc.identifier.citation | Pillay , S , Ariyaeeinia , A , Sivakumaran , P & Pawlewski , M 2012 , ' Effective speaker verification via dynamic mismatch compensation ' , IET Biometrics , vol. 1 , no. 2 , pp. 130-135 . https://doi.org/10.1049/iet-bmt.2012.0001 | |
dc.identifier.issn | 2047-4938 | |
dc.identifier.other | PURE: 992113 | |
dc.identifier.other | PURE UUID: 2da64798-b746-4dc5-b981-e8f8cd50eba1 | |
dc.identifier.other | Scopus: 84866860516 | |
dc.identifier.uri | http://hdl.handle.net/2299/9446 | |
dc.description.abstract | This paper presents a new approach to Condition-adjusted T-Norm (CT-Norm) for speaker verification under significant mismatched noise conditions. The study is motivated by the fact that, whilst the standard CT-Norm method offers enhanced accuracy under mismatched data conditions, its effectiveness reduces with the increased severity of such conditions. The proposed approach attempts to address this challenge by providing a more effective reduction of data mismatch through the incorporation of multi-SNR UBMs (universal background models). The effectiveness of the proposed approach is demonstrated through experiments based on examples of real-world noise. It is shown that the superiority of the approach over CT-Norm is particularly significant for such excessive levels of test data degradation considered in the study as 5 dB and below. The paper provides a description of the characteristics of the proposed approach and details the experimental analysis of its effectiveness under different noise conditions. | en |
dc.format.extent | 6 | |
dc.language.iso | eng | |
dc.relation.ispartof | IET Biometrics | |
dc.subject | Speaker verification; GMM-UBM; Multi-SNR GMM; Test-normalization | |
dc.title | Effective speaker verification via dynamic mismatch compensation | en |
dc.contributor.institution | Hertfordshire Business School | |
dc.contributor.institution | Social Sciences, Arts & Humanities Research Institute | |
dc.contributor.institution | School of Engineering and Technology | |
dc.contributor.institution | Science & Technology Research Institute | |
dc.contributor.institution | Centre for Engineering Research | |
dc.contributor.institution | Digital Media Processing and Biometrics | |
dc.contributor.institution | Smart Electronics Devices and Networks | |
dc.contributor.institution | Centre for Research on Management, Economy and Society | |
dc.contributor.institution | Group for Research on Innovation and Enterprise | |
dc.description.status | Peer reviewed | |
rioxxterms.version | VoR | |
rioxxterms.versionofrecord | https://doi.org/10.1049/iet-bmt.2012.0001 | |
rioxxterms.type | Journal Article/Review | |
herts.preservation.rarelyaccessed | true | |