Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/43613
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Electronic and Information Engineeringen_US
dc.creatorMak, MWen_US
dc.creatorPang, Xen_US
dc.creatorChien, JTen_US
dc.date.accessioned2016-06-07T06:22:40Z-
dc.date.available2016-06-07T06:22:40Z-
dc.identifier.issn2329-9290en_US
dc.identifier.urihttp://hdl.handle.net/10397/43613-
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.rights© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.rightsThe following publication M. Mak, X. Pang and J. Chien, "Mixture of PLDA for Noise Robust I-Vector Speaker Verification," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 1, pp. 130-142, Jan. 2016 is available at https://doi.org/10.1109/TASLP.2015.2499038.en_US
dc.subjectI-vectorsen_US
dc.subjectMixture of PLDAen_US
dc.subjectNoise robustnessen_US
dc.subjectProbabilistic LDAen_US
dc.subjectSpeaker verificationen_US
dc.titleMixture of PLDA for noise robust i-vector speaker verificationen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage130en_US
dc.identifier.epage142en_US
dc.identifier.volume24en_US
dc.identifier.issue1en_US
dc.identifier.doi10.1109/TASLP.2015.2499038en_US
dcterms.abstractIn real-world environments, noisy utterances with variable noise levels are recorded and then converted to i-vectors for cosine distance or PLDA scoring. This paper investigates the effect of noise-level variability on i-vectors. It demonstrates that noise-level variability causes the i-vectors to shift, causing the noise contaminated i-vectors to form clusters in the i-vector space. It also demonstrates that optimal subspaces for discriminating speakers are noise-level dependent. Based on these observations, this paper proposes using signal-to-noise ratio (SNR) of utterances as guidance for training mixture of PLDA models. To maximize the coordination among the PLDA models, mixtures of PLDA models are trained simultaneously via an EM algorithm using the utterances contaminated with noise at various levels. For scoring, given a test i-vector, the marginal likelihoods from individual PLDA models are linearly combined by the posterior probabilities of the test utterance's SNR. Verification scores are the ratio of the marginal likelihoods. Results based on NIST 2012 SRE suggest that the SNR-dependent mixture of PLDA is not only suitable for the situations where the test utterances exhibit a wide range of SNR, but also beneficial for the test utterances with unknown SNR distribution. Supplementary materials containing full derivations of the EM algorithms and scoring functions can be found in http://bioinfo.eie.polyu.edu.hk/mPLDA/SuppMaterials.pdf.en_US
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationIEEE/ACM transactions on audio, speech, and language processing, Jan. 2016, v. 24, no. 1, 2499038, p. 130-142en_US
dcterms.isPartOfIEEE/ACM transactions on audio, speech, and language processingen_US
dcterms.issued2016-01-
dc.identifier.scopus2-s2.0-84957057186-
dc.identifier.rosgroupid2015002449-
dc.description.ros2015-2016 > Academic research: refereed > Publication in refereed journalen_US
dc.description.oaAccepted Manuscripten_US
dc.identifier.FolderNumberEIE-0922-
dc.description.fundingSourceRGCen_US
dc.description.pubStatusPublisheden_US
dc.identifier.OPUS6613212-
Appears in Collections:Journal/Magazine Article
Files in This Item:
File Description SizeFormat 
Mak_Mixture_Plda_Noise.pdfPre-Published version1.65 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Final Accepted Manuscript
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

103
Last Week
0
Last month
Citations as of Mar 24, 2024

Downloads

41
Citations as of Mar 24, 2024

SCOPUSTM   
Citations

53
Last Week
1
Last month
Citations as of Mar 28, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.