VARIATIONAL MANIFOLD LEARNING FOR SPEAKER RECOGNITION
檔案
本條目沒有附加檔案。
日期
2017-01-01
類型
系所
期刊名稱
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
卷期與頁次
頁 4935–4939
ISSN
1520-6149
語言
英文
摘要
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.
關鍵詞
Probabilistic linear discriminant analysisdeep learningvariational manifold learningspeaker recognition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