News for hackers. Stuff that matters.
Re:Expressive Speech Synthesis with Tacotron by coryfklein on Tuesday March 27, 2018 @02:19PM (#16691290)
This is the audio equivalent of the Face2Face algorithm that takes one person's face and places it onto the character in a video, matching the latter subject's expressions.

This means we now live in a world where you can create a recording of Donald Trump saying, "I colluded with the Russians to rig the election," and not only have the voice sound like Trump but also bring along his personal expressive style so that it becomes indistinguishable from Trump himself.

Would love to see these two combined - make an audio-video recording of an actor confessing to election fraud, then use Face2Face to swap in Trump's face and use Tacotron to swap in his voice.

Re:Expressive Speech Synthesis with Tacotron by vbezhenar on Wednesday March 28, 2018 @12:57AM (#16695397)
Also this means that any confession evidence can not be trusted.
Re:Expressive Speech Synthesis with Tacotron by modeless on Tuesday March 27, 2018 @06:12PM (#16693252)
Note that this is separate from the other front page post about Google Cloud TTS powered by WaveNet. That's a product, while this is exciting new research (which will hopefully become part of a product).
Re:Expressive Speech Synthesis with Tacotron by visarga on Tuesday March 27, 2018 @03:59PM (#16692199)
This technology has been around for a year but we only got a few samples. I'm very excited. I use TTS to read back all the text I consume on PC.

This web demo allows you to enter your own text:

https://cloud.google.com/text-to-speech/

(select US American and Wavenet)

Re:Expressive Speech Synthesis with Tacotron by rryan on Tuesday March 27, 2018 @04:17PM (#16692331)
> This technology has been around for a year but we only got a few samples. I'm very excited. I use TTS to read back all the text I consume on PC.

Nope! These two papers are fresh work on prosody modeling. You can see the evolution of work this team has been publishing about here:

https://google.github.io/tacotron/

> This web demo allows you to enter your own text:

That web demo is unrelated to this. It's about a Google Cloud TTS API, which only includes WaveNet, not Tacotron.

https://cloudplatform.googleblog.com/2018/03/introducing-Clo...

Re:Expressive Speech Synthesis with Tacotron by polishTar on Tuesday March 27, 2018 @05:56PM (#16693118)
Re:Expressive Speech Synthesis with Tacotron by aero142 on Tuesday March 27, 2018 @08:13PM (#16694011)
A bunch of RPG games are going to have much better character voices after this.
Re:Expressive Speech Synthesis with Tacotron by coryfklein on Tuesday March 27, 2018 @06:05PM (#16693190)
That one was my favorite too. I just imagine some excited NPR reporter announcing that as a headline after a terrorist hostage situation.
Re:Expressive Speech Synthesis with Tacotron by John_KZ on Tuesday March 27, 2018 @10:13PM (#16694660)
Well, I guess it's time for authenticated phonecalls.
Re:Expressive Speech Synthesis with Tacotron by aaronharnly on Tuesday March 27, 2018 @08:01PM (#16693937)
Congratulations Daisy! This work is really impressive (and quite fun).