Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/43613
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electronic and Information Engineering | en_US |
dc.creator | Mak, MW | en_US |
dc.creator | Pang, X | en_US |
dc.creator | Chien, JT | en_US |
dc.date.accessioned | 2016-06-07T06:22:40Z | - |
dc.date.available | 2016-06-07T06:22:40Z | - |
dc.identifier.issn | 2329-9290 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/43613 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_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.rights | The 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.subject | I-vectors | en_US |
dc.subject | Mixture of PLDA | en_US |
dc.subject | Noise robustness | en_US |
dc.subject | Probabilistic LDA | en_US |
dc.subject | Speaker verification | en_US |
dc.title | Mixture of PLDA for noise robust i-vector speaker verification | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 130 | en_US |
dc.identifier.epage | 142 | en_US |
dc.identifier.volume | 24 | en_US |
dc.identifier.issue | 1 | en_US |
dc.identifier.doi | 10.1109/TASLP.2015.2499038 | en_US |
dcterms.abstract | In 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.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE/ACM transactions on audio, speech, and language processing, Jan. 2016, v. 24, no. 1, 2499038, p. 130-142 | en_US |
dcterms.isPartOf | IEEE/ACM transactions on audio, speech, and language processing | en_US |
dcterms.issued | 2016-01 | - |
dc.identifier.scopus | 2-s2.0-84957057186 | - |
dc.identifier.rosgroupid | 2015002449 | - |
dc.description.ros | 2015-2016 > Academic research: refereed > Publication in refereed journal | en_US |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | EIE-0922 | - |
dc.description.fundingSource | RGC | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 6613212 | - |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Mak_Mixture_Plda_Noise.pdf | Pre-Published version | 1.65 MB | Adobe PDF | View/Open |
Page views
103
Last Week
0
0
Last month
Citations as of Mar 24, 2024
Downloads
41
Citations as of Mar 24, 2024
SCOPUSTM
Citations
53
Last Week
1
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.