Speech Modelling Using Subspace and EM Techniques.
Gavin SmithJoão F. G. de FreitasTony RobinsonMahesan NiranjanPublished in: NIPS (1999)
Keyphrases
- expectation maximization
- speech recognition
- subspace learning
- audio visual
- principal component analysis
- em algorithm
- speech signal
- speaker recognition
- maximum likelihood
- high dimensional
- feature space
- pattern recognition
- image segmentation
- text to speech
- speech synthesis
- broadcast news
- linear subspace
- endpoint detection
- subspace clustering
- mixture model
- neural network
- gaussian mixture model
- emotion recognition
- high dimensional data
- speaker identification
- unsupervised learning
- hidden markov models
- kernel based nonlinear