Estimation of Articulatory Trajectories Based on Gaussian Mixture Model (GMM) With Audio-Visual Information Fusion and Dynamic Kalman Smoothing.
I. Yücel ÖzbekMark Hasegawa-JohnsonMübeccel DemireklerPublished in: IEEE Trans. Speech Audio Process. (2011)
Keyphrases
- gaussian mixture model
- information fusion
- audio visual
- multi stream
- mixture model
- emotion recognition
- multi modal
- data fusion
- speaker recognition
- feature vectors
- maximum likelihood
- em algorithm
- soft computing
- visual information
- expectation maximization
- gaussian mixture
- multimedia
- visual data
- feature space
- background subtraction
- speech recognition
- gaussian mixture modeling
- speaker identification
- maximum likelihood criterion
- pattern recognition
- generative model
- image classification
- probabilistic model