A model-selection-based self-splitting Gaussian mixture learning with application to speaker identification
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
2639 | en_US |
dc.citation.issue |
17 | en_US |
dc.citation.spage |
2626 | en_US |
dc.citation.volume |
2004 | en_US |
dc.citation.woscount |
4 | |
dc.contributor.author |
Cheng, SS | en_US |
dc.contributor.author |
Wang, HM | en_US |
dc.contributor.author |
Fu, HC | en_US |
dc.contributor.department |
資訊工程學系 | zh_TW |
dc.contributor.department |
Department of Computer Science | en_US |
dc.date.accessioned |
2014-12-08T15:37:10Z | |
dc.date.available |
2014-12-08T15:37:10Z | |
dc.date.issued |
2004-12-15 | en_US |
dc.description.abstract |
We propose a self-splitting Gaussian mixture learning (SGML) algorithm for Gaussian mixture modelling. The SGML algorithm is deterministic and is able to find an appropriate number of components of the Gaussian mixture model (GMM) based on a self-splitting validity measure, Bayesian information criterion (BIC). It starts with a single component in the feature space and splits adaptively during the learning process until the most appropriate number of components is found. The SGML algorithm also performs well in learning the GMM with a given component number. In our experiments on clustering of a synthetic data set and the text-independent speaker identification task, we have observed the ability of the SGML for model-based clustering and automatically determining the model complexity of the speaker GMMs for speaker identification. | en_US |
dc.identifier.doi |
10.1155/S1110865704407100 | en_US |
dc.identifier.issn |
1110-8657 | en_US |
dc.identifier.journal |
EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1155/S1110865704407100 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/25551 | |
dc.identifier.wosnumber |
WOS:000227870700003 | |
dc.language.iso |
en_US | en_US |
dc.subject |
unsupervised learning | en_US |
dc.subject |
Gaussian mixture modelling | en_US |
dc.subject |
Bayesian information criterion | en_US |
dc.subject |
speaker identification | en_US |
dc.title |
A model-selection-based self-splitting Gaussian mixture learning with application to speaker identification | en_US |
dc.type |
Article | en_US |
檔案
- 000227870700003.pdf (1.14 MB, Adobe PDF)
所屬典藏: 期刊論文
引用此條目
Cheng, S., Wang, H., & Fu, H. (2004). A model-selection-based self-splitting Gaussian mixture learning with application to speaker identification. EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2004(17), 2626–2639. https://doi.org/10.1155/S1110865704407100
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/11536/25551