Speaker Identification by Aggregating Gaussian Mixture Models (GMMs) Based on Uncorrelated MFCC-derived Features.
Amita PalSmarajit BoseGopal K. BasakAmitava MukhopadhyayPublished in: Int. J. Pattern Recognit. Artif. Intell. (2014)
Keyphrases
- gaussian mixture model
- speaker identification
- mel frequency cepstral coefficients
- feature vectors
- speaker recognition
- mixture model
- feature space
- probabilistic neural network
- audio signal
- feature extraction
- linear predictive
- em algorithm
- language identification
- feature set
- expectation maximization
- image features
- maximum likelihood
- speech recognition
- feature selection
- non stationary
- image classification
- speech signal
- classification accuracy
- model selection
- probabilistic model
- object recognition
- bayesian information criterion
- acoustic features