from Hacker News

Char2Wav: End-To-End Speech Synthesis

by serialx on 2/22/17, 2:00 AM with 24 comments

• by rspeer on 2/22/17, 7:00 AM

  I am getting tired of people implementing "deep learning to convert foo into bar" and staking a claim on the name "foo2bar".

  It leads to "AI hallucination", where even if "foo2bar" doesn't work, people assume that it's the one right AI for turning foo into bar. When someone gets better at turning foo into bar, the typical response will be "is that just foo2bar?"

  This happened absurdly backwards with doc2vec, which after word2vec everyone talked about as if it were a real thing, until Radim Řehůřek finally made a reasonable implementation of it under that name.

• by BugsJustFindMe on 2/22/17, 11:59 AM

  http://www.josesotelo.com/speechsynthesis/files/wav/blizzard...

  I have not laughed this hard in a long time.

• by billconan on 2/22/17, 2:16 AM

  the demo page isn't clearly presented.

  for example, on this page, only spanish has the char2wav label.

  http://www.josesotelo.com/speechsynthesis/

  It's unclear which results are the output of the model.

• by verytrivial on 2/22/17, 10:01 AM

  Many of the synth voices sound to my ear very similar to people who are either drunk or have a brain injury. I'm not complaining, it's an interesting parallel.

• by option_greek on 2/22/17, 3:54 AM

  So how does this work? It's not very clear from the article.

• by wernerb on 2/22/17, 1:26 PM

  Proceeding to feed this Paul Bettany's "Jarvis" from some movies...

• by teddyh on 2/22/17, 7:56 AM

  I’d like to feed The Chaos to it and see how it fares.