Adobe is using AI to break apart messy audio
Adobe is working on a new audio tool designed to separate different layers of sound within a single recording. The tool is called Project Sound Lift and can use AI to separate things like applause from the sound of someone’s voice.
As shown in a demo sent to The edge, all you have to do is import an audio file into the app and then choose the sound you want the tool to filter out. There are many options to choose from, including clapping, laughing, alarms, speech, crowds, traffic, keyboarding, 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, such as 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 change the volume of background noise while improving the clarity of the main track. Things are still early, though – Adobe’s Project Sound Lift is considered one of Adobe’s “sneak” previews, which means we’ll have to wait a little longer until a final release of the tool is published (if Adobe decides to do so at all).
There are other tools with similar functionality, such as Supertone is clear And Goyo Voice Separator, but they only offer options for splitting and changing the file’s ambience, vocals, and vocal reverb. Adobe’s Project Sound Lift, on the other hand, is designed to capture 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 vocals from a cassette recording and used AI to separate the overwhelming piano music from Lennon’s vocals.
