Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model.
Xiang LiSongxiang LiuMax W. Y. LamZhiyong WuChao WengHelen MengPublished in: INTERSPEECH (2023)
Keyphrases
- denoising
- probabilistic model
- speech synthesis
- text to speech
- nonlinear diffusion
- prediction accuracy
- diffusion processes
- image denoising
- audio visual
- speech recognition
- language model
- total variation
- prosodic features
- linear prediction
- wavelet domain
- speech signal
- multi stream
- noisy images
- natural images
- denoising algorithm
- prediction model
- image processing
- noise removal
- prediction algorithm
- neural network
- diffusion model
- diffusion process
- prediction error
- automatic speech recognition
- spoken language
- multi modal
- hidden markov models
- gaussian noise