Using Wavelets and Gaussian Mixture Models for Audio Classification.
Ching-Hua ChuanSusan VasanaAsai AsaithambiPublished in: ISM (2012)
Keyphrases
- gaussian mixture model
- feature vectors
- speech music discrimination
- mixture model
- speaker identification
- feature extraction
- classification accuracy
- feature space
- maximum likelihood criterion
- probability density
- feature selection
- speaker recognition
- pattern classification
- em algorithm
- maximum likelihood
- signal processing
- machine learning
- expectation maximization
- multimedia
- density estimation
- pattern recognition
- gaussian mixture
- image processing
- mel frequency cepstral coefficients
- variational bayes
- probabilistic neural network
- decision trees
- audio visual
- probabilistic model
- text classification
- wavelet transform
- language model
- unsupervised learning
- image classification