High-Acoustic Fidelity Text To Speech Synthesis With Fine-Grained Control Of Speech Attributes.
Rafael ValleJoão Felipe SantosKevin J. ShihRohan BadlaniBryan CatanzaroPublished in: ICASSP (2023)
Keyphrases
- fine grained
- text to speech synthesis
- text to speech
- coarse grained
- access control
- underwater vehicles
- tightly coupled
- prosodic features
- speech recognition
- bird species
- speech recognition systems
- massively parallel
- databases
- xml documents
- high level
- data model
- automatic speech recognition
- acoustic signal
- speech sounds