Live data from Hacker News

Adobe demos “photoshop for audio,” lets you edit speech as easily as text

arstechnica.com

1–10 of 58 posts

Re: Adobe demos “photoshop for audio,” lets you edit speech as easily as text

#5
post #4

How long before video and audio evidence will not longer be admissible in court? 2030?

Photos are still admissible, despite Photoshop existing for several decades.

Not to mention, notoriously unreliable eyewitness accounts.

Re: Adobe demos “photoshop for audio,” lets you edit speech as easily as text

#6
post #2

I thought it sounded badly cut when he moved wife in the sentence but adding new text was pretty amazing.

It did sound like they picked the right things to say. I won't be surprised if the extra words appear in the 20 minutes of training speech. Either way even if it's not as magical as they try to make it its still extremely useful for the voiceover industry.

Re: Adobe demos “photoshop for audio,” lets you edit speech as easily as text

#7
post #2

I thought it sounded badly cut when he moved wife in the sentence but adding new text was pretty amazing.

Only in the same way that a photo edited in Photoshop 1 looked incredibly obvious though. In 10 generations of the software it'll be really hard to spot where speech has been changed.

Re: Adobe demos “photoshop for audio,” lets you edit speech as easily as text

#8
post #4

How long before video and audio evidence will not longer be admissible in court? 2030?

Photos are still admissible, despite Photoshop existing for several decades.

People were convincingly doctoring photos looong before Photoshop.

Re: Adobe demos “photoshop for audio,” lets you edit speech as easily as text

#9
post #4

How long before video and audio evidence will not longer be admissible in court? 2030?

Photos are still admissible, despite Photoshop existing for several decades.

To be fair on that front: all evidence can be challenged as being false/fake/etc

Re: Adobe demos “photoshop for audio,” lets you edit speech as easily as text

#10
Sounds a lot like this: https://youtu.be/xzL-pxcpo-E?t=933

IRCAM has been doing some really cool stuff in this area for a long time. Check out their pages on corpus-based synthesis for example: http://imtr.ircam.fr/imtr/Corpus_Based_Synthesis

Post reply on HN