Please use this identifier to cite or link to this item: http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1883
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGhaemmaghami, H.
dc.contributor.authorRaman, M.H.
dc.contributor.authorHimawan, I.
dc.contributor.authorDean, D.
dc.contributor.authorAhilan, K.
dc.contributor.authorSridharan, S.
dc.contributor.authorFookes, C.
dc.date.accessioned2021-03-15T07:52:10Z
dc.date.accessioned2022-06-27T10:02:18Z-
dc.date.available2021-03-15T07:52:10Z
dc.date.available2022-06-27T10:02:18Z-
dc.date.issued2016
dc.identifier.citationGhaemmaghami, H., Rahman, M. H., Himawan, I., Dean, D., Kanagasundaram, A., Sridharan, S., & Fookes, C. (2016). Speakers in the wild (SITW): The QUT speaker recognition system. In Proceedings of the 17th Annual Conference of the International Speech Communication Association (ISCA): (pp. 838-842). International Speech Communication Association (ISCA).en_US
dc.identifier.urihttp://repo.lib.jfn.ac.lk/ujrr/handle/123456789/1883-
dc.description.abstractThis paper presents the QUT speaker recognition system, as a competing system in the Speakers In The Wild (SITW) speaker recognition challenge. Our proposed system achieved an overall ranking of second place, in the main core-core condition evaluations of the SITW challenge. This system uses an ivector/ PLDA approach, with domain adaptation and a deep neural network (DNN) trained to provide feature statistics. The statistics are accumulated by using class posteriors from the DNN, in place of GMM component posteriors in a typical GMM-UBM i-vector/PLDA system. Once the statistics have been collected, the i-vector computation is carried out as in a GMM-UBM based system. We apply domain adaptation to the extracted i-vectors to ensure robustness against dataset variability, PLDA modelling is used to capture speaker and session variability in the i-vector space, and the processed i-vectors are compared using the batch likelihood ratio. The final scores are calibrated to obtain the calibrated likelihood scores, which are then used to carry out speaker recognition and evaluate the performance of the system. Finally, we explore the practical application of our system to the core-multi condition recordings of the SITW data and propose a technique for speaker recognition in recordings with multiple speakers.en_US
dc.language.isoenen_US
dc.titleSPEAKERS IN THE WILD (SITW): The QUT Speaker Recognition Systemen_US
dc.typeArticleen_US
Appears in Collections:Electrical & Electronic Engineering

Files in This Item:
File Description SizeFormat 
SPEAKERS IN THE WILD (SITW) The QUT Speaker Recognition System.pdf69.11 kBAdobe PDFThumbnail
View/Open


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