News for hackers. Stuff that matters.
Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by The_rationalist on Wednesday June 10, 2020 @07:30AM (#23475911)
It seems that contrary to their sota Baseline, at least for English, text to speech is a solved problem (on their metric MOS) https://paperswithcode.com/sota/speech-synthesis-on-north-am... The SOTA has a 4.526 MOS vs their 4.084 and baseline of 4.41 and human performance is 4.55

There are no comments on this comment yet.