Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis.
Alexandra VioniMyrsini ChristidouNikolaos EllinasGeorgios VamvoukakisPanos KakoulidisTaehoon KimJune Sig SungHyoungmin ParkAimilios ChalamandarisPirros TsiakoulisPublished in: CoRR (2021)
Keyphrases
- speech synthesis
- end to end
- prosodic features
- speech recognition
- text to speech
- vocal tract
- congestion control
- multipath
- admission control
- ad hoc networks
- high bandwidth
- language model
- wireless ad hoc networks
- rate allocation
- pattern recognition
- real world
- hidden markov models
- automatic speech recognition
- information theoretic
- content delivery
- scalable video
- neural network
- probabilistic model
- image processing
- machine learning