WaveNet: A Generative Model for Raw Audio

Re:WaveNet: A Generative Model for Raw Audio by Houshalter on Thursday September 08, 2016 @11:10PM (#12459419)

And who says it can't understand the material? There have been recurrent networks trained that can translate between languages, or predict the next word in a sentence, at remarkable accuracy. Combined with wavenet this could be quite effective.

[ Parent | on HN ]

Re:WaveNet: A Generative Model for Raw Audio by thomasahle on Friday September 09, 2016 @02:30AM (#12460027)

There could be cases where the intonation is dependent on things entirely outside of the book. If say a politician does something in the writing that is far from what we would expect them to do in today's world.

[ Parent | on HN ]

Re:WaveNet: A Generative Model for Raw Audio by visarga on Friday September 09, 2016 @12:09PM (#12463524)

How about we allow annotation of text with prosody cues? Mark the words you want stressed. We already use question and exclamation marks.

[ Parent | on HN ]

Re:WaveNet: A Generative Model for Raw Audio by atty79 on Friday September 09, 2016 @10:45PM (#12467407)

I'd love that. Writing is a poor representation of language. It'd be nice to bring it up a notch. Here's a suggestion in a paper I wrote on better second language acquisition. https://www.researchgate.net/publication/261022308_BETTER_SE...

[ Parent | on HN ]

Re:WaveNet: A Generative Model for Raw Audio by spiritus_ on Friday September 09, 2016 @05:14AM (#12460588)

Like traditional audio books can capture perfectly what you're referring to...

[ Parent | on HN ]

Re:WaveNet: A Generative Model for Raw Audio by ycombinatorMan on Friday September 09, 2016 @11:38AM (#12463202)

They can, though?

[ Parent | on HN ]