News for hackers. Stuff that matters.

A comment on An open source implementation of DeepVoice 3: 2000-Speaker Neural Text-to-Speech.

Re:An open source implementation of DeepVoice 3: 2000-Speake... by rglullis on Thursday April 26, 2018 @05:53AM (#16930428)
If I understood it correctly, the datasets being used are all in the order of ~20 hours. Could the results be improved with a different dataset? Say, Mozilla's Common Voice[1]? They are already at 350 hours of labeled speech.

[1]: https://voice.mozilla.org

[ Parent | on HN ]
Re:An open source implementation of DeepVoice 3: 2000-Speake... by IshKebab on Thursday April 26, 2018 @08:42AM (#16931307)
Maybe, but Google's tacotron2 also used about 24 hours of speech and gives results that are indistinguishable from humans.
[ Parent | on HN ]