Evaluating expressiveness of a voice-guided speech re-synthesis system using vocal prosodic parameters.
Yuan-Yi FanSoyoung ShinVids SamantaPublished in: IUI Companion (2019)
Keyphrases
- text to speech
- emotion recognition
- speech recognition
- text to speech synthesis
- speech signal
- prosodic features
- speech synthesis
- synthesized speech
- parameter values
- speaker verification
- noisy environments
- audio visual
- speech quality
- speech sounds
- sensitivity analysis
- expressive power
- automatic speech recognition
- measured data
- computational properties
- expectation maximization
- maximum likelihood
- voice activity detection
- neural network
- acoustic features
- word processing
- language acquisition
- parameter space
- sentiment analysis
- non stationary
- multi modal
- image sequences