Speaker recognition by means of acoustic and phonetically informed GMMs.
Sandro CumaniPietro LafaceFarzana KulsoomPublished in: INTERSPEECH (2015)
Keyphrases
- speaker recognition
- gaussian mixture model
- mel frequency cepstral coefficients
- mixture model
- vector quantization
- speaker identification
- feature vectors
- maximum likelihood
- expectation maximization
- em algorithm
- speech signal
- probabilistic neural network
- speaker verification
- particle swarm optimization
- model selection
- neural network
- wavelet transform
- positive and negative
- multimedia