DMCA
Adjusting mixture weights of gaussian mixture model via regularized probabilistic latent semantic analysis (2005)
Cached
Download Links
- [www.cs.cmu.edu]
- [www.cs.cmu.edu]
- [www.cse.msu.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | In PAKDD |
| Citations: | 13 - 0 self |
BibTeX
@INPROCEEDINGS{Si05adjustingmixture,
author = {Luo Si and Rong Jin},
title = {Adjusting mixture weights of gaussian mixture model via regularized probabilistic latent semantic analysis},
booktitle = {In PAKDD},
year = {2005},
pages = {622--631}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Mixture models, such as Gaussian Mixture Model, have been widely used in many applications for modeling data. Gaussian mixture model (GMM) assumes that data points are generated from a set of Gaussian models with the same set of mixture weights. A natural extension of GMM is the probabilistic latent semantic analysis (PLSA) model, which assigns different mixture weights for each data point. Thus, PLSA is more flexible than the GMM method. However, as a tradeoff, PLSA usually suffers from the overfitting problem. In this paper, we propose a regularized probabilistic latent semantic analysis model (RPLSA), which can properly adjust the amount of model flexibility so that not only the training data can be fit well but also the model is robust to avoid the overfitting problem. We conduct empirical study for the application of speaker identification to show the effectiveness of the new model. The experiment results on the NIST speaker recognition dataset indicate that the RPLSA model outperforms both the GMM and PLSA models substantially. The principle of RPLSA of appropriately adjusting model flexibility can be naturally extended to other applications and other types of mixture models. 1
Keyphrases
gaussian mixture model mixture weight probabilistic latent semantic analysis data point mixture model model flexibility experiment result gmm method training data many application natural extension speaker identification plsa model fit well nist speaker recognition dataset overfitting problem rplsa model gaussian model empirical study new model different mixture weight
