Speech fine structure contains critical temporal cues to support speech segmentation.
Xiangbin TengGregory B. CoganDavid PoeppelPublished in: NeuroImage (2019)
Keyphrases
- speech recognition
- speech signal
- multiscale
- speech synthesis
- image segmentation
- dialogue system
- prosodic features
- text to speech
- audio visual
- shape prior
- region growing
- spatio temporal
- probabilistic model
- segmentation method
- segmentation algorithm
- noisy environments
- multiple cues
- end users
- temporal structure
- word segmentation
- emotion recognition
- visual patterns
- spatial and temporal
- motion estimation
- automatic speech recognition
- visual cues
- temporal patterns
- temporal constraints
- image regions