VARIATIONAL MANIFOLD LEARNING FOR SPEAKER RECOGNITION
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
4939 | en_US |
dc.citation.spage |
4935 | en_US |
dc.contributor.author |
Chien, Jen-Tzung | en_US |
dc.contributor.author |
Hsu, Cheng-Wei | en_US |
dc.contributor.department |
電機工程學系 | zh_TW |
dc.contributor.department |
Department of Electrical and Computer Engineering | en_US |
dc.date.accessioned |
2018-08-21T05:56:55Z | |
dc.date.available |
2018-08-21T05:56:55Z | |
dc.date.issued |
2017-01-01 | en_US |
dc.description.abstract |
This 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.identifier.issn |
1520-6149 | en_US |
dc.identifier.journal |
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/146832 | |
dc.identifier.wosnumber |
WOS:000414286205019 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
Probabilistic linear discriminant analysis | en_US |
dc.subject |
deep learning | en_US |
dc.subject |
variational manifold learning | en_US |
dc.subject |
speaker recognition | en_US |
dc.title |
VARIATIONAL MANIFOLD LEARNING FOR SPEAKER RECOGNITION | en_US |
dc.type |
Proceedings Paper | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 會議論文
引用此條目
Chien, J.-T., & Hsu, C.-W. (2017). VARIATIONAL MANIFOLD LEARNING FOR SPEAKER RECOGNITION. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 4935–4939. https://ir.lib.nycu.edu.tw/handle/11536/146832
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/146832