A Gaussian mixture regression approach toward modeling the affective dynamics between acoustically-derived vocal arousal score (VC-AS) and internal brain fMRI bold signal response.
Hsuan-Yu ChenYu-Hsien LiaoHeng-Tai JanLi-Wei KuoChi-Chun LeePublished in: ICASSP (2016)
Keyphrases
- gaussian mixture
- functional magnetic resonance imaging
- event related
- human brain
- cognitive states
- activation detection
- brain activity
- emotion recognition
- em algorithm
- activation patterns
- human subjects
- gaussian mixture model
- brain images
- high dimensional
- signal processing
- mixtures of gaussians
- expectation maximization
- affective states
- probability density function
- mental states
- data analysis
- emotional state
- correlation analysis
- covariance matrix
- medical images
- information processing
- closed form
- feature selection