Going blind and learning to love audiobooks

Re:Going blind and learning to love audiobooks by johansch on Monday December 25, 2017 @11:35AM (#16004680)

With the rate speech synthesis is developing, it's probably going to be hard to distinguish between human speakers and synthetic speakers in a few years from now.

[ Parent | on HN ]

Re:Going blind and learning to love audiobooks by gradys on Monday December 25, 2017 @11:37AM (#16004689)

See https://google.github.io/tacotron/publications/tacotron2/ind...

And the HN discussion: https://news.ycombinator.com/item?id=15962543

[ Parent | on HN ]

Re:Going blind and learning to love audiobooks by JoshTriplett on Monday December 25, 2017 @12:55PM (#16005004)

I'm really looking forward to those actually being available to use.

[ Parent | on HN ]

Re:Going blind and learning to love audiobooks by johansch on Monday December 25, 2017 @01:23PM (#16005129)

I've just started to use AWS Polly in some demos, but the speech synthesis quality feels 2-3 years old at least :/

[ Parent | on HN ]

Re:Going blind and learning to love audiobooks by johansch on Monday December 25, 2017 @12:54PM (#16005000)

I think what's missing is to understand and adapt the speech rhythm and pauses based on the language. At first sight I would say that this requires human intuition, but then again, lots of literature is repetative, so I think ML could actually work quite well well, with actual understanding of the text, given enough data.

[ Parent | on HN ]