Tag Archives: Walter Werzowa

Finishing Beethoven’s unfinished 10th Symphony

Throughout the project, Beethoven’s genius loomed. Circe Denyer

This is an artificial intelligence (AI) story set to music. Professor Ahmed Elgammal (Director of the Art & AI Lab at Rutgers University located in New Jersey, US) has a September 24, 2021 essay posted on The Conversation (and, then, in the Smithsonian Magazine online) describing the AI project and upcoming album release and performance (Note: A link has been removed),

When Ludwig van Beethoven died in 1827, he was three years removed from the completion of his Ninth Symphony, a work heralded by many as his magnum opus. He had started work on his 10th Symphony but, due to deteriorating health, wasn’t able to make much headway: All he left behind were some musical sketches.

A full recording of Beethoven’s 10th Symphony is set to be released on Oct. 9, 2021, the same day as the world premiere performance scheduled to take place in Bonn, Germany – the culmination of a two-year-plus effort.

These excerpts from the Elgammal’s September 24, 2021 essay on the The Conversation provide a summarized view of events. By the way, this isn’t the first time an attempt has been made to finish Beethoven’s 10th Symphony (Note: Links have been removed),

Around 1817, the Royal Philharmonic Society in London commissioned Beethoven to write his Ninth and 10th symphonies. Written for an orchestra, symphonies often contain four movements: the first is performed at a fast tempo, the second at a slower one, the third at a medium or fast tempo, and the last at a fast tempo.

Beethoven completed his Ninth Symphony in 1824, which concludes with the timeless “Ode to Joy.”

But when it came to the 10th Symphony, Beethoven didn’t leave much behind, other than some musical notes and a handful of ideas he had jotted down.

There have been some past attempts to reconstruct parts of Beethoven’s 10th Symphony. Most famously, in 1988, musicologist Barry Cooper ventured to complete the first and second movements. He wove together 250 bars of music from the sketches to create what was, in his view, a production of the first movement that was faithful to Beethoven’s vision.

Yet the sparseness of Beethoven’s sketches made it impossible for symphony experts to go beyond that first movement.

In early 2019, Dr. Matthias Röder, the director of the Karajan Institute, an organization in Salzburg, Austria, that promotes music technology, contacted me. He explained that he was putting together a team to complete Beethoven’s 10th Symphony in celebration of the composer’s 250th birthday. Aware of my work on AI-generated art, he wanted to know if AI would be able to help fill in the blanks left by Beethoven.

Röder then compiled a team that included Austrian composer Walter Werzowa. Famous for writing Intel’s signature bong jingle, Werzowa was tasked with putting together a new kind of composition that would integrate what Beethoven left behind with what the AI would generate. Mark Gotham, a computational music expert, led the effort to transcribe Beethoven’s sketches and process his entire body of work so the AI could be properly trained.

The team also included Robert Levin, a musicologist at Harvard University who also happens to be an incredible pianist. Levin had previously finished a number of incomplete 18th-century works by Mozart and Johann Sebastian Bach.

… We didn’t have a machine that we could feed sketches to, push a button and have it spit out a symphony. Most AI available at the time couldn’t continue an uncompleted piece of music beyond a few additional seconds.

We would need to push the boundaries of what creative AI could do by teaching the machine Beethoven’s creative process – how he would take a few bars of music and painstakingly develop them into stirring symphonies, quartets and sonatas.

Here’s Elgammal’s description of the difficulties from an AI perspective, from the September 24, 2021 essay (Note: Links have been removed),

First, and most fundamentally, we needed to figure out how to take a short phrase, or even just a motif, and use it to develop a longer, more complicated musical structure, just as Beethoven would have done. For example, the machine had to learn how Beethoven constructed the Fifth Symphony out of a basic four-note motif.

Next, because the continuation of a phrase also needs to follow a certain musical form, whether it’s a scherzo, trio or fugue, the AI needed to learn Beethoven’s process for developing these forms.

The to-do list grew: We had to teach the AI how to take a melodic line and harmonize it. The AI needed to learn how to bridge two sections of music together. And we realized the AI had to be able to compose a coda, which is a segment that brings a section of a piece of music to its conclusion.

Finally, once we had a full composition, the AI was going to have to figure out how to orchestrate it, which involves assigning different instruments for different parts.

And it had to pull off these tasks in the way Beethoven might do so.

The team tested its work, from the September 24, 2021 essay, Note: A link has been removed,

In November 2019, the team met in person again – this time, in Bonn, at the Beethoven House Museum, where the composer was born and raised.

This meeting was the litmus test for determining whether AI could complete this project. We printed musical scores that had been developed by AI and built off the sketches from Beethoven’s 10th. A pianist performed in a small concert hall in the museum before a group of journalists, music scholars and Beethoven experts.

We challenged the audience to determine where Beethoven’s phrases ended and where the AI extrapolation began. They couldn’t.

A few days later, one of these AI-generated scores was played by a string quartet in a news conference. Only those who intimately knew Beethoven’s sketches for the 10th Symphony could determine when the AI-generated parts came in.

The success of these tests told us we were on the right track. But these were just a couple of minutes of music. There was still much more work to do.

There is a preview of the finished 10th symphony,

Beethoven X: The AI Project: III Scherzo. Allegro – Trio (Official Video) | Beethoven Orchestra Bonn

Modern Recordings / BMG present as a foretaste of the album “Beethoven X – The AI Project” (release: 8.10.) the edit of the 3rd movement “Scherzo. Allegro – Trio” as a classical music video. Listen now: https://lnk.to/BeethovenX-Scherzo

Album pre-order link: https://lnk.to/BeethovenX

The Beethoven Orchestra Bonn performing with Dirk Kaftan and Walter Werzowa a great recording of world-premiere Beethoven pieces. Developed by AI and music scientists as well as composers, Beethoven’s once unfinished 10th symphony now surprises with beautiful Beethoven-like harmonics and dynamics.

For anyone who’d like to hear the October 9, 2021 performance, Sharon Kelly included some details in her August 16, 2021 article for DiscoverMusic,

The world premiere of Beethoven’s 10th Symphony on 9 October 2021 at the Telekom Forum in Bonn, performed by the Beethoven Orchestra Bonn conducted by Dirk Kaftan, will be broadcast live and free of charge on MagentaMusik 360.

Sadly, the time is not listed but MagentaMusik 360 is fairly easy to find online.

You can find out more about Professor Elgammal on his Rutgers University profile page. Elgammal has graced this blog before in an August 16, 2019 posting “AI (artificial intelligence) artist got a show at a New York City art gallery“. He’s mentioned in an excerpt about 20% of the way down the page,

Ahmed Elgammal thinks AI art can be much more than that. A Rutgers University professor of computer science, Elgammal runs an art-and-artificial-intelligence lab, where he and his colleagues develop technologies that try to understand and generate new “art” (the scare quotes are Elgammal’s) with AI—not just credible copies of existing work, like GANs do. “That’s not art, that’s just repainting,” Elgammal says of GAN-made images. “It’s what a bad artist would do.”

Elgammal calls his approach a “creative adversarial network,” or CAN. It swaps a GAN’s discerner—the part that ensures similarity—for one that introduces novelty instead. The system amounts to a theory of how art evolves: through small alterations to a known style that produce a new one. That’s a convenient take, given that any machine-learning technique has to base its work on a specific training set.

Finally, thank you to @winsontang whose tweet led me to this story.