Diffusion-based accent modelling in speech synthesis.
Kamil DejaGeorgi TinchevMarta CzarnowskaMarius CotescuJasha DroppoPublished in: INTERSPEECH (2023)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- vocal tract
- hidden markov models
- automatic speech recognition
- prosodic features
- language model
- speech corpus
- pattern recognition
- speech signal
- information systems
- anisotropic diffusion
- diffusion processes
- diffusion process
- information diffusion
- noisy environments
- neural network
- data sets
- real time
- human brain
- noisy images
- information technology