An Improved Speaker Identification System Using Automatic Split-Merge Incremental Learning (A-SMILE) of Gaussian Mixture Models.
Ayoub BouzianeJamal KharroubiArsalane ZarghiliPublished in: CSOC (1) (2017)
Keyphrases
- gaussian mixture model
- incremental learning
- speaker identification
- speaker recognition
- mixture model
- probabilistic neural network
- feature vectors
- em algorithm
- maximum likelihood
- learning process
- supervised learning
- expectation maximization
- mel frequency cepstral coefficients
- pattern recognition
- feature extraction
- image processing
- data mining
- data sets