完整後設資料紀錄
DC 欄位語言
dc.contributor.authorChien, Jen-Tzungen_US
dc.contributor.authorHsu, Cheng-Weien_US
dc.date.accessioned2018-08-21T05:56:55Z-
dc.date.available2018-08-21T05:56:55Z-
dc.date.issued2017-01-01en_US
dc.identifier.issn1520-6149en_US
dc.identifier.urihttp://hdl.handle.net/11536/146832-
dc.description.abstractThis paper presents a variational manifold learning for speaker recognition based on the probabilistic linear discriminant analysis (PLDA) using i-vectors. A latent variable model is introduced to compensate the constraints of the linearity in PLDA scoring and the high dimensionality in using i-vectors. A deep variational learning is formulated to jointly optimize three objectives including a regularization for variational distributions, a reconstruction based on PLDA and a manifold learning for neighbor embedding. A stochastic gradient variational Bayesian algorithm is developed to optimize the variational lower bound of log likelihood where the expectation in the objectives is estimated via a sampling method. Interestingly, the latent variables in the proposed variational manifold PLDA (vm-PLDA) are capable of decoding or reconstructing the i-vectors. The experiments on visualization and speaker recognition show the merits of vm-PLDA in manifold learning and classification.en_US
dc.language.isoen_USen_US
dc.subjectProbabilistic linear discriminant analysisen_US
dc.subjectdeep learningen_US
dc.subjectvariational manifold learningen_US
dc.subjectspeaker recognitionen_US
dc.titleVARIATIONAL MANIFOLD LEARNING FOR SPEAKER RECOGNITIONen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)en_US
dc.citation.spage4935en_US
dc.citation.epage4939en_US
dc.contributor.department電機工程學系zh_TW
dc.contributor.departmentDepartment of Electrical and Computer Engineeringen_US
dc.identifier.wosnumberWOS:000414286205019en_US
顯示於類別:會議論文