Mixture of Factor Analyzers Using Priors From Non-Parallel Speech for Voice Conversion.
Zhizheng WuTomi KinnunenEngsiong ChngHaizhou LiPublished in: IEEE Signal Process. Lett. (2012)
Keyphrases
- text to speech
- voice activity detection
- emotion recognition
- speech recognition
- fundamental frequency
- speech signal
- speech quality
- speech recognition errors
- speech synthesis
- noisy environments
- synthesized speech
- prior information
- prosodic features
- speech sounds
- audio visual
- bayesian framework
- broadcast news
- maximum a posteriori
- multi class