Combining GMM's with suport vector machines for text-independent speaker verification.
Jamal KharroubiDijana Petrovska-DelacrétazGérard CholletPublished in: INTERSPEECH (2001)
Keyphrases
- speaker verification
- speaker recognition
- gaussian mixture model
- noisy environments
- prosodic features
- audio visual
- feature vectors
- text mining
- acoustic features
- information retrieval
- language identification
- multilayer perceptron
- speaker identification
- emotion recognition
- vector quantization
- text data
- using artificial neural networks
- multi modal
- keywords
- feature space
- multiscale
- genetic algorithm