3WRBM-based speech factor modeling for arbitrary-source and non-parallel voice conversion.
Toru NakashikaYasuhiro MinamiPublished in: EUSIPCO (2016)
Keyphrases
- text to speech
- speech synthesis
- parallel processing
- parallel implementation
- database
- modeling method
- parallel computing
- voice activity detection
- speech recognition errors
- prosodic features
- spoken language
- massively parallel
- shared memory
- factor analysis
- audio visual
- speech recognition
- feature extraction
- search engine