One specific project that Adobe is working on with Princeton University is called Project VoCo, which received a sneak preview at Adobe’s MAX 2016 conference. Adobe developer Zeyu Jin showed off the technology in a brief presentation, describing the process as essentially Photoshop for audio, as The Verge reports.
According to the demonstration, Project VoCo enables a user to add words to a speech recording that are not actually included in the original. The software uses an algorithm that requires roughly 20 minutes of speech recording for a given individual, which analyzes the sound and then replicates the individual’s voice. Then, Project VoCo can add new, unspoken words into recordings.
Adobe has a rather innocent idea of what the technology might be used for, as it indicated in an official statement: “When recording voiceovers, dialogue, 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.”
Just as with Photoshopped images, however, it’s easy to imagine much more nefarious uses for such a technology. In fact, if the algorithm is good enough and can create a synthetic voice that’s identical to the actual speaker’s, then the very notion of using sound recordings as evidence could go out the window. Like many technologies, then, Project VoCo has both its light and its dark sides.
There’s no information on if or when Project VoCo technology will make it into a commercially available product. Certainly, it’s not particularly surprising that someone like Adobe is working on the ability to create artificial recordings, and it would be more surprising than not if we don’t see it hitting the market at some point in the future.
