Adobe Promises a Photoshop like AI for Sound

Design software giant Adobe is trying to raise the bar with the all new AI-powered Project Sound Lift. The one-click solution can dissect speech recordings into distinct tracks, separating voices, non-speech sounds, and background noise in videos.

The company claims that Project Sound Lift is a one-click method through which users will be able to manipulate audio recordings, leveraging AI to independently enhance, transform, and control speech and sound. Adobe’s Enhance Speech technology—now available in Adobe applications like Premiere Pro—is integrated within Project Sound Lift allowing creators to craft studio-quality audio content easily.

There is a growing need for the tool in the market as poor audio quality remains a persisting challenge in the creator’s economy. Artists work around audio issues caused by wind interference, sub-optimal microphone locations, crowd noise and other sound nuisances, any of which can render videos unusable but Adobe has introduced AI as the saviour.

Developed by speech AI researchers at Adobe Research the project was announced at MAX Japan as part of Adobe’s “Sneaks” showcase, where Adobe engineers and research scientists offer sneak peeks at prototype ideas and technologies.

In the demo shared with AIM, Adobe boasted how its project is tailored to pick up specific sound, can separate and manage a wide array of audio “events” from daily life scenarios, including splitting speech, applause, laughter, alarms, crowds, and other noises into distinct tracks. However, as with any technological leap Adobe is not the only nor first one to offer these capabilities. 

Lalal.ai already does all of the above tasks. Alongside the user have its iOS and Android apps to work on the go. Audo.ai is carving its niche in noise reduction. Moreover, the open-source Ultimate Vocal Remover GUI has been quietly serving as a constant option for audio manipulation, focusing primarily on vocal separation but also adaptable for denoising purposes.