RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis
Year: 2021
Type: conference-paper
Authors: Kevin J. Shih, Rafael Valle, Rohan Badlani, Adrian Łańcucki, Wei Ping, Bryan Catanzaro
Institutions: Nvidia (United Kingdom), Stanford University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: text-to-speech, parallel flow, speech synthesis
Open Access status: closed
OpenAlex ID: W3194000401
