Multi-source based acoustic model for speech synthesis.
Jianhua TaoYongguo KangPublished in: SSW (2004)
Keyphrases
- speech synthesis
- multi source
- speech recognition
- data fusion
- text to speech
- information fusion
- vocal tract
- prosodic features
- single source
- multiple sources
- data sources
- data integration
- multiple data sources
- soft clustering
- community detection
- case study
- feature extraction
- social networks
- artificial intelligence
- neural network
- database