Re:Researchers achieve speech recognition milestone
by mintplant on Wednesday September 14, 2016 @05:43PM
(#12501445)
How about the inverse process -- speech synthesis? Anyone know what the state of the art is in that field? The tech has been getting steadily better but we still seem a ways away from passable machine-generated audiobooks, for example.
[ Parent
| on HN ]
Re:Researchers achieve speech recognition milestone
by Devid2014 on Wednesday September 14, 2016 @05:44PM
(#12501454)
Like thins one ?
WaveNet: A Generative Model for Raw Audio https://deepmind.com/blog/wavenet-generative-model-raw-audio...
Re:Researchers achieve speech recognition milestone
by mintplant on Wednesday September 14, 2016 @05:49PM
(#12501490)
That's very cool, thanks for the link! From the comparison, the audio quality is clearly improved and they eliminated the sort of digital "wobble" that I usually associate with TTS. Intonation is still a bit off, though. Will check out their paper.
Re:Researchers achieve speech recognition milestone
by marmshallow on Wednesday September 14, 2016 @06:36PM
(#12501791)
I've wondered the same thing! How much work is being done in the area of making Siri and OK Google sound more human-like?
Re:Researchers achieve speech recognition milestone
by snowwrestler on Thursday September 15, 2016 @01:41AM
(#12503717)
Computer generated speech (Siri and voiceover) was one of the areas that Apple said they were applying AI techniques to improve.