Speaker recognition based on variational Bayesian method.
Tatsuya ItoKei HashimotoYoshihiko NankakuAkinobu LeeKeiichi TokudaPublished in: INTERSPEECH (2008)
Keyphrases
- speaker recognition
- bayesian methods
- gaussian mixture model
- speaker verification
- vector quantization
- probabilistic neural network
- image segmentation
- gaussian processes
- bayesian framework
- model selection
- speaker identification
- learning algorithm
- mixture model
- em algorithm
- machine learning
- machine learning methods
- speech recognition
- hyperparameters
- speech signal
- maximum a posteriori
- machine learning algorithms
- feature vectors