Synthesize Speech In Any Voice,New Software that can can cause controversy

 

Good luck ever trusting a recording again. as it is right now, records done and presented in court as evidence will hardly have any value. 
A low quality video has emerged from the Adobe conference MAX showing a demo for a prototype of a new software, called Project VoCo, that appears to be a Photoshop for audio.The program is shown synthesizing a man's voice to read different sentences based on the software's analysis of a real clip of him speaking. Just copy and paste to change it from "I kissed my dog and my wife" to "I kissed my wife and my wife." Or even insert entirely new words—they still sound eerily authentic.In case you were confused about what the software's intended purpose is, Adobe issued a statement:

When recording voiceovers, dialog, and narration, people would often like to change or insert a word or a few words due to either a mistake they made or simply because they would like to change part of the narrative. We have developed a technology called Project VoCo in which you can simply type in the word or words that you would like to change or insert into the voiceover. The algorithm does the rest and makes it sound like the original speaker said those words.

The crowd laughs and cheers uproariously as the program is demod, seemingly unaware of the disturbing implications for a program like this especially in the context of an election cycle where distortions in truth are commonplace. Being able to synthesize —or claim that real audio was synthesized—would only muddy waters even further.

Somehow the clip also involves the comedian Jordan Peele, present at the conference, whose shocked expression is the only indication that anyone there is thinking about how this software will be used out in the real world.

Share this

Share on FacebookPlus on Google+