[NJTechDiv] Fwd: Adobe is using AI to break apart messy audio
Mario Brusco
mrb620 at hotmail.com
Thu Nov 16 15:47:29 UTC 2023
From: tech-vi at groups.io <tech-vi at groups.io> On Behalf Of David Goldfield
Sent: Wednesday, November 15, 2023 8:30 PM
To: List <tech-vi at groups.io>
Subject: [Tech-VI] Adobe is using AI to break apart messy audio
The Verge - All Posts - Wednesday, November 15, 2023 at 4:00 PM
Adobe is using AI to break apart messy audio
Adobe’s AI-powered Project Sound Lift can separate background noise
from the sound of someone’s voice.
Illustration by Alex Castro / The Verge
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 <https://product.supertone.ai/clear> and Goyo’s voice
separator <https://goyo.app/>, 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
<https://www.theverge.com/2023/11/2/23943290/now-and-then-the-beatles-new-song-ai>
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.
https://www.theverge.com/2023/11/15/23962452/adobe-project-sound-lift-ai-audio-tool
<https://www.theverge.com/2023/11/15/23962452/adobe-project-sound-lift-ai-audio-tool>
David Goldfield
Assistive Technology Specialist
Subscribe to the Tech-VI announcement list to receive news and updates
regarding the blindness assistive technology space
Email: Tech-VI+subscribe at groups.io <mailto:Tech-VI+subscribe at groups.io>
WWW.DavidGoldfield.com <http://www.davidgoldfield.com/>
More information about the NJTechDiv
mailing list