Multidimensional model based speech signal representations for automatic speaker identification .
Pravinkumar PremakanthanWasfy B. MikhaelPublished in: Circuits, Signals, and Systems (2004)
Keyphrases
- speaker identification
- speech signal
- speech recognition
- speaker recognition
- noisy environments
- language identification
- gaussian mixture model
- probabilistic neural network
- automatic speech recognition
- non stationary
- spectral analysis
- hidden markov models
- feature extraction
- broadcast news
- sound source
- mixture model
- multi modal
- machine learning
- acoustic features
- mel frequency cepstral coefficients