Sir Paul McCartney has announced the creation of a new Beatles song with the help of AI. Using a technique called “stem separation,” the technology was employed to isolate John Lennon’s voice from an old demo.

Although the title of the song has not been released, experts believe it is Lennon’s unfinished work, “Now and Then.” Peter Jackson used similar AI tools to separate the Beatles’ voices from background noise for his documentary “Get Back.”

When it came to making what Sir Paul McCartney called “the last Beatles record,” he said, “We were able to take John’s voice (from an old audio cassette) and get it pure through this AI. So then, we could mix the record as you would normally do… So there’s a good side to it and a scary side — and we’ll just have to see where that leads.”

Don’t confuse this headline as having anything to do with ChatGPT or Generative AI or any other “groundbreaking” AI technology. Stem separation has been around for quite a while. If you’re wondering what stem separation actually means, here’s a visual metaphor for music mixing:

Imagine you start with two pitchers: one filled with red liquid, the other filled with blue. You mix them together to get a pitcher filled with purple liquid. (That’s the finished mix.) Is there any way to separate the pitcher of purple liquid into its original red and blue pitchers (stems)? For audio recordings, the answer is yes. Here’s a short list of tools you can use (and there are dozens more):

  • iZotope RX10 (or RX9)
  • Lalal
  • XTRAX Stems
  • fadr
  • VirtualDJ

I’m not endorsing any of the above, but I have used the iZotope suite for years and the tools are amazing. I’ve also used Lalal to separate voice overs from background music and background noise, and it works as advertised.

If you want to learn more about the power of narrow-focused AI in the context of generative AI applications or autonomous agents, sign up for our free online course, Generative AI for Execs.

Author’s note: This is not a sponsored post. I am the author of this article and it expresses my own opinions. I am not, nor is my company, receiving compensation for it.

About Shelly Palmer

Shelly Palmer is the Professor of Advanced Media in Residence at Syracuse University’s S.I. Newhouse School of Public Communications and CEO of The Palmer Group, a consulting practice that helps Fortune 500 companies with technology, media and marketing. Named LinkedIn’s “Top Voice in Technology,” he covers tech and business for Good Day New York, is a regular commentator on CNN and writes a popular daily business blog. He's a bestselling author, and the creator of the popular, free online course, Generative AI for Execs. Follow @shellypalmer or visit



PreviousAmazon Testing Generative AI Review Summaries NextMusic Industry Hits Twitter to the Tune of $250 Million

Get Briefed Every Day!

Subscribe to my daily newsletter featuring current events and the top stories in technology, media, and marketing.