Voice GMM modelling for FESTIVAL/MBROLA emotive TTS synthesis.
Mauro NicolaoCarlo DrioliPiero CosiPublished in: INTERSPEECH (2006)
Keyphrases
- text to speech
- gaussian mixture model
- voice activity detection
- speech synthesis
- prosodic features
- emotion recognition
- gaussian mixture modeling
- speaker recognition
- texture synthesis
- gaussian mixture
- mixture model
- mel frequency cepstral coefficients
- case study
- information retrieval
- word processing
- image processing
- genetic algorithm