The Beatles Come Together for the Last Time

AI in music has done its magic in assembling a song from old recordings for The Beatles that span over four decades.

The new song will be called Now and Then. It has been assembled from an old recording of the late John Lennon in his house in New York in 1979 playing the piano and singing. Artificial Intelligence in this case has been helpful because it was used to extract sections from the noisy recording that are usable.

These have been combined with guitar tracks from the late George Harrison, which were recorded in 1995 during efforts to complete the song. The project was reportedly canceled due to poor sound quality, which AI has now resolved.

Finally, new recordings from Paul McCartney and Ringo Starr from earlier this year were added. The single will be released on November 2nd at 2pm GMT and will bookend the band’s career by including Love Me Do, The Beatles’ first ever single, as a B-side.

For months, McCartney has teased the song’s existence in interviews, saying in a statement, “There it was, John’s voice, crystal clear. It’s quite emotional. And we all play on it, it’s a genuine Beatles recording. In 2023 to still be working on Beatles music, and about to release a new song the public haven’t heard, I think it’s an exciting thing.”

WingNut Films, the production company of film director Peter Jackson, is credited on the single for “source separation,” but the company was unavailable for an interview.

The company, which worked on the Lord of the Rings trilogy, also produced the Get Back documentary, which included footage of The Beatles performing Let it Be.

WingNut engineers worked on 60 hours of recording captured by a single microphone that picked up the musicians’ instruments in a noisy jumble rather than a carefully crafted mix when creating Now and Then. The microphone also picked up background noise and chatter, rendering much of the recording useless.

To assist editors in creating a workable documentary, the team decided to use AI to separate the dialogue from other noises. Finally, the team was able to create bespoke AI capable of removing all background noise and isolating not only speech but also the sound of each instrument played in a band.

According to Jess Aslan of Goldsmiths, University of London, The Beatles’ track is an interesting experiment because it was done transparently with the permission of the band’s living members, but AI is a double-edged sword that also poses risks to artists.

“One significant issue is that generative AI is squeezing the already extremely narrow creative job market,” she says. “Another is that of ownership, in that these large-scale models are in effect bypassing copyright laws and reconfiguring artists’ data without consent. In this case AI was of aid to the music industry.

Die-hard fans cannot wait for the 2nd of November.  

Tomorrow is the day I’ll be thankful for AI.

Inside Telecom provides you with an extensive list of content covering all aspects of the tech industry. Keep an eye on our Tech sections to stay informed and up-to-date with our daily articles.