Text Independent Automatic Speaker Recognition System Using Mel-Frequency Cepstrum Coefficient and Gaussian Mixture Models.
Alfredo MaesaFabio GarziaMichele ScarpinitiRoberto CusaniPublished in: J. Information Security (2012)
Keyphrases
- gaussian mixture model
- speaker recognition
- speaker identification
- mixture model
- em algorithm
- speech music discrimination
- mel frequency cepstral coefficients
- speaker verification
- feature vectors
- cepstral coefficients
- feature space
- vector quantization
- keywords
- text mining
- information retrieval
- covariance matrices
- probabilistic neural network
- expectation maximization
- maximum likelihood
- probability density function
- density estimation
- gaussian mixture
- speech signal
- speech recognition
- probability density
- probabilistic model
- finite mixtures