Model Adaptation Approach to Speech Synthesis with Diverse Voices and Styles.
Junichi YamagishiTakao KobayashiMakoto TachibanaKatsumi OgataYuji NakanoPublished in: ICASSP (4) (2007)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- vocal tract
- prosodic features
- real world
- automatic speech recognition
- wide variety
- speech corpus
- hidden markov models
- database
- artificial intelligence
- databases
- information technology
- learning environment
- social interaction
- e learning
- information systems
- search engine
- real time