Speaker Model Clustering to Construct Background Models for Speaker Verification

Basit Öğe Kaydı
dc.authoridCevik, Ulus/0000-0002-0956-9725
dc.authoridTufekci, Zekeriya/0000-0001-7835-2741
dc.contributor.authorDisken, Gokay
dc.contributor.authorTufekci, Zekeriya
dc.contributor.authorCevik, Ulus
dc.date.accessioned2025-01-06T17:38:06Z
dc.date.available2025-01-06T17:38:06Z
dc.date.issued2017
dc.description.abstractConventional speaker recognition systems use the Universal Background Model (UBM) as an imposter for all speakers. In this paper, speaker models are clustered to obtain better imposter model representations for speaker verification purpose. First, a UBM is trained, and speaker models are adapted from the UBM. Then, the k-means algorithm with the Euclidean distance measure is applied to the speaker models. The speakers are divided into two, three, four, and five clusters. The resulting cluster centers are used as background models of their respective speakers. Experiments showed that the proposed method consistently produced lower Equal Error Rates (EER) than the conventional UBM approach for 3, 10, and 30 seconds long test utterances, and also for channel mismatch conditions. The proposed method is also compared with the i-vector approach. The three-cluster model achieved the best performance with a 12.4% relative EER reduction in average, compared to the i-vector method. Statistical significance of the results are also given.
dc.identifier.doi10.1515/aoa-2017-0014
dc.identifier.endpage135
dc.identifier.issn0137-5075
dc.identifier.issn2300-262X
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85016282458
dc.identifier.scopusqualityQ3
dc.identifier.startpage127
dc.identifier.urihttps://doi.org/10.1515/aoa-2017-0014
dc.identifier.urihttps://hdl.handle.net/20.500.14669/2479
dc.identifier.volume42
dc.identifier.wosWOS:000395358100014
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherPolska Akad Nauk, Polish Acad Sciences, Inst Fundamental Tech Res Pas
dc.relation.ispartofArchives of Acoustics
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_20241211
dc.subjectGaussian mixture models
dc.subjectk-means
dc.subjectimposter models
dc.subjectspeaker clustering
dc.subjectspeaker verification
dc.titleSpeaker Model Clustering to Construct Background Models for Speaker Verification
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu