According to foreign media reports,AdobeA new audio tool is being developed that uses AI technology to separate different sound layers in mixed recordings. The tool, called Project Sound Lift, can automatically detect different elements in a recording, such as applause, laughter, background noise, etc., and separate them from the human voice to generate independent audio files.
Users only need to import the audio file into the tool, select the type of sound they want to filter out, and Project Sound Lift will use AI to detect and separate different sounds. In this way, the volume of background noise can be adjusted individually while enhancing the clarity of foreground vocals. Compared to other tools that only provide simple audio separation functions, Project Sound Lift specializes in separating specific sounds and provides more sophisticated audio editing capabilities.
Although the tool is still in the proof-of-concept stage, it demonstrates the potential of AI in the field of audio processing. Similar technology has been used in the production of the Beatles' new song, using AI to extract John Lennon's vocals from the mixtape. If launched, Project Sound Lift may have a revolutionary impact on audio editing and mixing technology. This shows that Adobe continues to use AI to innovate audio and video technology and provide creators with more powerful creative tools.