Preliminary experiments toward automatic generation of new TTS voices from recorded speech alone.
Ryuki TachibanaTohru NaganoGakuto KurataMasafumi NishimuraNoboru BabaguchiPublished in: INTERSPEECH (2007)
Keyphrases
- text to speech
- speech synthesis
- text to speech synthesis
- prosodic features
- automatically generate
- english text
- speech recognition
- automatic speech recognition
- word processing
- generation method
- broadcast news
- automatically generating
- neural network
- visual information
- non stationary
- genetic algorithm
- machine learning