F0 modeling for isarn speech synthesis using deep neural networks and syllable-level feature representation.
Pongsathon JanyoiPusadee SeresangtakulPublished in: Int. Arab J. Inf. Technol. (2020)
Keyphrases
- feature representation
- speech synthesis
- neural network
- prosodic features
- feature level
- speech recognition
- feature extraction
- text to speech
- feature representations
- sparse representation
- low dimensional
- feature set
- high dimensional
- training set
- pattern recognition
- vocal tract
- nearest neighbor
- image features
- viewpoint
- face recognition