Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs.
Danoush HosseinzadehSridhar KrishnanPublished in: MMSP (2007)
Keyphrases
- speaker recognition
- gaussian mixture model
- mel frequency cepstral coefficients
- speech signal
- speaker identification
- feature vectors
- feature extraction
- feature set
- speech recognition
- feature space
- speaker verification
- probabilistic neural network
- vector quantization
- extracted features
- mixture model
- low level
- expectation maximization
- em algorithm
- maximum likelihood
- multiresolution
- multiscale