Emotional speaker recognition based on i-vector through Atom Aligned Sparse Representation.
Li ChenYingchun YangPublished in: ICASSP (2013)
Keyphrases
- sparse representation
- speaker recognition
- gaussian mixture model
- dictionary learning
- speaker verification
- probabilistic neural network
- sparse coding
- vector quantization
- image classification
- feature vectors
- speaker identification
- high dimensional data
- face recognition
- pattern classification
- emotion recognition
- image patches
- image representation
- signal processing
- dimensionality reduction
- speech signal
- speech recognition
- mixture model
- multiscale
- emotional state
- em algorithm
- low dimensional
- image data
- image processing