Hidden Markov model based voice conversion using dynamic characteristics of speaker.
Eun-Kyoung KimSangho LeeYung-Hwan OhPublished in: EUROSPEECH (1997)
Keyphrases
- dynamic characteristics
- synthesized speech
- prosodic features
- speaker verification
- neural network model
- power system
- speech recognition
- transmission line
- speech sounds
- emotion recognition
- speaker recognition
- speech synthesis
- text to speech
- speaker diarization
- automatic speech recognition
- audio visual
- mel frequency cepstral coefficients
- voice and data services
- speaker dependent
- machine learning
- voice activity detection
- computational intelligence
- control system