Deep Voice 3: 2000-Speaker Neural Text-to-Speech.
Wei PingKainan PengAndrew GibianskySercan Ömer ArikAjay KannanSharan NarangJonathan RaimanJohn MillerPublished in: CoRR (2017)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- network architecture
- text to speech synthesis
- multimodal interaction
- word processing
- programming tool
- english text
- vocal tract
- neural network
- speaker verification
- bio inspired
- neural model
- deep learning
- associative memory
- biologically plausible
- automatic speech recognition
- speech recognition
- pattern recognition