Designing Japanese speech database covering wide range in prosody for hybrid speech synthesizer.
Hiromichi KawanamiTsuyoshi MasudaTomoki TodaKiyohiro ShikanoPublished in: INTERSPEECH (2002)
Keyphrases
- text to speech
- speech synthesis
- database
- wide range
- speech recognition
- text to speech synthesis
- prosodic features
- audio visual
- databases
- speech signal
- vocal tract
- multi stream
- neural network
- data model
- database systems
- word processing
- endpoint detection
- recognition engine
- english text
- query language
- speaker recognition
- broadcast news
- spoken language
- metadata
- language acquisition
- noisy environments
- data mining
- dialogue system
- database queries