RealTalk Speech Synthesis

#1

Post by Peroni » Thu, May 16, 2019, 12:22 PM UTC

RealTalk Speech Synthesis
medium.com

Re: RealTalk Speech Synthesis

#2

Post by EamonnMR » Thu, May 16, 2019, 12:52 PM UTC

At least to my ears, this sounds better than Lyrebird did when it was posted here. Bravo!

Re: RealTalk Speech Synthesis

#3

Post by grenoire » Thu, May 16, 2019, 1:08 PM UTC

Hot damn, as someone who has listened to a few JRE episodes, it is... quite good. What really struck me was its ability to recreate words that were (I'm guessing) weren't said by him in the past. Impressive!

Re: RealTalk Speech Synthesis

#4

Post by Donald » Thu, May 16, 2019, 1:10 PM UTC

  Because of this, at this time we will not be releasing our research, model or datasets publicly.

Has OpenAI's handling of GPT-2 inadvertently provided political cover for commercial organizations who would love to claim they engage with the ML research community but would actually prefer to contribute nothing other than medium articles?

Re: RealTalk Speech Synthesis

#5

Post by masswerk » Thu, May 16, 2019, 1:13 PM UTC

Impressive (really), but it raises a more philosophical question (as in practical ethics): do we really want voice-bots to blend in perfectly, or should they better feature distinctive marks (like a rather monotonous personality)?

[Edit: This is not so much about DeepFakes, as discussed in the article, but more about a general level of implementation.]

Re: RealTalk Speech Synthesis

#6

Post by bitwize » Thu, May 16, 2019, 1:13 PM UTC

Well, now we know what's going to happen to all that Alexa voice data.

Re: RealTalk Speech Synthesis

#7

Post by RandomInteger4 » Thu, May 16, 2019, 1:25 PM UTC

Sounds good in terms of lack of pauses between words and his general voice, but you can tell something is off due to the cadence and at times it seems like words trail off into breathlessness.

Re: RealTalk Speech Synthesis

#8

Post by mwcampbell » Thu, May 16, 2019, 1:41 PM UTC

There's a telltale discontinuity in the rise of the voice on the word "chimps" in the sentence "and these chimps have been working out hard". I wonder if future generations of kids will have to be trained to spot such things.

Re: RealTalk Speech Synthesis

#9

Post by mikeash » Thu, May 16, 2019, 1:45 PM UTC

masswerk wrote: post #5

Impressive (really), but it raises a more philosophical question (as in practical ethics): do we really want voice-bots to blend in perfectly, or should they better feature distinctive marks (like a rather monotonous personality)? [Edit: This is not so much about DeepFakes, as discussed in the article, but more about a general level of implementation.]

If perfect imitations are outlawed, only outlaws will have perfect imitations.

I’m not sure how useful that question is. If it can be done then it will be, and we’ll have to deal with it whether we want it or not.

Re: RealTalk Speech Synthesis

#10

Post by agentultra » Thu, May 16, 2019, 1:52 PM UTC

Remember in Fahrenheit 451 where Guy Montag's partner is glued to the Wall? A screen where she participates in her favorite shows and the audience and cast members talk directly to her?

Read in a modern context I don't think Guy was merely burning books in service to an authoritarian government. I think he kept the books because he was becoming an outsider. He didn't want to participate in the world of the Wall and consent to the expectations and norms of his society. And the firemen were there to ensure everyone participated.