On automatic voice casting for expressive speech: Speaker recognition vs. speech classification.
Nicolas ObinAxel RoebelGrégoire BachmanPublished in: ICASSP (2014)
Keyphrases
- speaker recognition
- mel frequency cepstral coefficients
- probabilistic neural network
- speaker identification
- gaussian mixture model
- speaker verification
- speech signal
- vector quantization
- pattern classification
- pattern recognition
- speech recognition
- machine learning
- emotion recognition
- classification accuracy
- support vector machine svm
- image classification
- noisy environments
- feature space
- text classification
- image compression
- audio visual
- feature vectors
- feature extraction
- feature selection
- multi modal
- automatic speech recognition
- multiscale
- image segmentation
- neural network