Adobe is using AI to break apart messy audio

Adobe is working on a new audio tool designed to break apart different layers of sound within a single recording. The tool is called Project Sound Lift, and it can use AI to separate elements like applause from the sound of someone’s voice.

As shown in a demo sent to The Verge, all you have to do is import an audio file into the application, then choose which sound you want the tool to filter out. There are quite a few options to choose from, including applause, laughter, alarms, speech, crowds, traffic, typing, and more. Project Sound Lift will automatically detect each sound and spit out separate files containing the background noise and the track you want to prioritize, like someone’s voice or the sound of an instrument.

You can then import and edit each track individually in Adobe Premiere Pro, allowing you to tweak the volume of background noise, while enhancing the clarity of the main track. Things are still early, though — Adobe’s Project Sound Lift is being branded as one of Adobe’s “Sneak” previews, which means we’ll have to wait a bit longer until we see a final version of the tool released (if Adobe decides to at all).

There are some other tools out there with similar capabilities, such as Supertone’s Clear and Goyo’s voice separator, but they only offer options to split up and tweak the file’s ambience, voice, and voice reverb. Adobe’s Project Sound Lift, on the other hand, is tailored to pick up specific sounds.

This is the same type of technology used to restore and release the first Beatles song in almost 30 years: “Now and Then.” Producers were tasked with restoring the sound of John Lennon’s voice from a cassette tape recording and used AI to separate overpowering piano music from Lennon’s vocals.