In our new paper [https://t.co/KPLEtjlVr3] we propose EATS: End-to-End Adversarial Text-to-Speech, which allows for speech synthesis directly from text or phonemes without the need for multi-stage training pipelines or additional supervision.
— DeepMind (@DeepMind) June 8, 2020
Audio: https://t.co/iQki8MRfgk pic.twitter.com/h8Ye4FfC0M
from Twitter https://twitter.com/DeepMind
June 08, 2020 at 05:05AM
via IFTTT
No comments:
Post a Comment