An Upper Bound on Normalized Maximum Likelihood Codes for Gaussian Mixture Models.
So HiraiKenji YamanishiPublished in: CoRR (2017)
Keyphrases
- gaussian mixture model
- upper bound
- normalized maximum likelihood
- lower bound
- change point detection
- mixture model
- em algorithm
- speaker recognition
- feature vectors
- expectation maximization
- code length
- feature space
- maximum likelihood
- gaussian distribution
- error correction
- spatially adaptive
- outlier detection
- minimum description length
- mdl principle
- probability density function
- non stationary
- feature extraction
- generative model
- bayesian networks