Voice activity detection based on sequential Gaussian mixture model with maximum likelihood criterion.
Zhan ShenJianguo WeiWenhuan LuJianwu DangPublished in: ISCSLP (2016)
Keyphrases
- gaussian mixture model
- maximum likelihood criterion
- voice activity detection
- mixture model
- em algorithm
- expectation maximization
- speaker recognition
- gaussian mixture
- maximum likelihood
- background subtraction
- feature vectors
- feature space
- noisy environments
- speaker identification
- gaussian mixture modeling
- probability density function
- gaussian distribution
- speech recognition
- neural network
- object detection
- bayesian information criterion
- computer vision