Acoustic-phonetic features for refining the explicit speech segmentation.
Antonio Marcos SelminiFábio ViolaroPublished in: INTERSPEECH (2007)
Keyphrases
- emotional speech
- speech segments
- speech recognition
- speech recognition systems
- automatic speech recognition
- emotion recognition
- speech sounds
- medical images
- segmentation accuracy
- emotion classification
- segmentation algorithm
- segmentation method
- feature extraction
- level set
- low level
- gaussian mixture model
- shape prior
- speech retrieval
- audio visual
- mel frequency cepstral coefficients
- speaker identification
- speech signal
- image regions
- image analysis
- pattern recognition