The music industry is facing a revolution called artificial intelligence. Generative AI models that create great fake songs — like Drake’s and The Weeknd’s — are one side of that coin, but there’s another. Which allows, for example, the Beatles to release a new song this year, more than half a century after they last recorded together.
Paul McCartney. Beatles member on the BBC that he used an artificial intelligence system to “extract” Lennon’s voice from an old demo to complete a song for the compilation due out this year, though McCartney gave no specific dates.
All thanks to the bar. The song “Now And Then” is expected to be a song written by John Lennon in 1978. It is part of a series of songs that Lennon recorded on a boom box in his New York apartment, which led to a cassette called “For Paul.”
An old acquaintance. The song could have been included as part of the Beatles’ “reunion song” earlier in 1995, because at that time the group members were compiling their anthology. Yoko Ono, widow of John LennonHe sent the tape to McCartney at the time.
I tried before. Producer Jeff Lynne reworked two songs from that tape, “Free as a bird” and “Real love,” as the Beatles’ first “new material” in 25 years. A restoration of “Now and Then” was also attempted, but although it contains a chorus “it’s completely lacking in the verses”, Lynn explained then. “We did the backing track, and it’s such a tough effort that we didn’t really finish it.”
So it can not be. McCartney stated in an interview with the BBC that George Harrison refused to work on that song because the quality of Lennon’s voice was “rubbish”. For him it “wasn’t titled very well, it needed some work, but it had a great chorus and John sang over it. But George didn’t like it, and because the Beatles were democrats, we didn’t put it out.”
The idea. The idea came according to the artist’s statements After the Get Back documentary which premiered in 2021 by Peter Jackson who narrated the production of the album “Let It Be”. In this project, Jackson used a computer system to be able to separate and extract sounds from ambient noise and from his own equipment to get the clearest and purest sound possible.
John Lennon’s voice. McCartney claimed that Jackson was able to extract John’s voice from a poor quality cassette tape. “We had John’s voice and piano and he could separate them using AI,” the artist explained. The film director and his team simply helped name and distinguish Lennon’s voice from his guitar, for example, and from there they could extract Lennon’s legendary voice.
to remix. Thanks to this technology, it was possible to separate Lennon’s voice to remix it as had been done for years, already including the rest of the necessary instruments and vocals. What was achieved, then, was to record the original song, but to do so at a much higher quality and without losing Lennon’s original voice in it.
Beware, “This Is Really Lennon”. McCartney was amazed at what this technology made possible, but also warned of the dangers it posed, for example recreating Lennon’s voice as he sang other songs. “This is just artificial intelligence”, and in contrast to that possible future, in this song “This is really Lennon”.
Image | Wikimedia
In Xataka | Shock of an era: Such was the mysterious break-up of the Beatles seen after 50 years
“Travel junkie. Coffee lover. Incurable social media evangelist. Zombie maven.”