Fine-grained robust prosody transfer for single-speaker neural text-to-speech.
Viacheslav KlimkovSrikanth RonankiJonas RohnkeThomas DrugmanPublished in: CoRR (2019)
Keyphrases
- fine grained
- text to speech
- prosodic features
- speech synthesis
- coarse grained
- access control
- speech recognition
- speaker verification
- tightly coupled
- text to speech synthesis
- neural network
- programming tool
- massively parallel
- network architecture
- noisy environments
- spontaneous speech
- word processing
- multi modal
- hidden markov models
- data lineage