Adobe is working on a new audio application designed to separate different audio layers in a recording. The tool is called Project Sound Lift, and it uses artificial intelligence to extract, for example, applause from a speaker’s voice.
All the user needs to do is import the audio file into the app and then select which audio you want the tool to filter out. There are quite a few options to choose from including applause, laughter, alarms, speech, crowd, traffic, typing and more. Project Sound Lift automatically detects each sound and displays individual files that contain 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 audio individually in Adobe Premiere Pro, allowing you to adjust the volume of the background noise while increasing the volume of the main track.
This is the same type of technology that was used to restore and release a Beatles song. The producers were tasked with recreating the sound of John Lennon’s voice from the cassette tape and using artificial intelligence to separate the piano music from Lennon’s vocals.
Source: The Verge
