News for hackers. Stuff that matters.
Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by seedless-sensat on Tuesday June 09, 2020 @10:38PM (#23473330)
Speech samples in the DeepMind publication post: https://deepmind.com/research/publications/End-to-End-Advers...
Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by scotth on Tuesday June 09, 2020 @11:48PM (#23473709)
"Ablation: No Monotonic Interpolation" is my favorite — wait for it...
Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by lunixbochs on Wednesday June 10, 2020 @12:36AM (#23473950)
I ran into that with tacotron sometimes too
Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by ryanmjacobs on Tuesday June 09, 2020 @11:36PM (#23473641)
I think this is a better link and should have been posted instead. These sound samples are pretty wild! Scary accurate.
Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by ArtWomb on Wednesday June 10, 2020 @08:07AM (#23476162)
Thanks! You can also experiment with DeepMind's WaveNet using GCP TTS Service (free tier):

https://cloud.google.com/text-to-speech

Re:DeepMind introduces ‘EATS’: adversarial, end-to-end appro... by stubish on Wednesday June 10, 2020 @12:01AM (#23473787)
Do I still hear a bit of 'autotune' in there, or am I projecting?

I wonder if DeepMind will tackle emoting; they certainly have something good enough for voice overs in a business context.