Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis.
Julian ZaïdiHugo SeutéBenjamin van NiekerkMarc-André CarbonneauPublished in: CoRR (2021)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- vocal tract
- noisy environments
- hidden markov models
- language model
- automatic speech recognition
- pattern recognition
- neural network
- speech corpus
- bayesian networks
- databases
- parameter tuning
- speech signal
- speaker identification
- video sequences
- computer vision
- real world