from sketch to symphony: how ai and a team of experts finished beethoven’s 10th

© Crice Denyer/CC BY

Beethoven was commissioned in 1817 to write two symphonies: he completed his Ninth Symphony in 1824, but the 10th remained in its early stages at the time of his death three years later

- Crice Denyer/CC BY

Ludwig van Beethoven died in 1827, three years after completing his Ninth Symphony, which many consider his masterpiece. He had started to work on a 10th Symphony, but the deterioration of his state of health did not allow him to complete this project, which remained in the draft stage.

Since then, musicologists and Beethoven lovers have wondered – and lament not knowing – what this symphony could have become. Now, thanks to the work of a team of music historians, musicologists, composers and computer engineers, Beethoven’s vision has come to life.

Responsible for the artificial intelligence (AI) side of the project, I led a scientific team from the AI start-up Playform that taught a machine Beethoven’s entire body of work and his creative process.

A full recording of his 10th Symphony was released on 9 October 2021, and was performed on stage for the first time in Bonn, Germany, crowning more than two years of effort.

Past attempts hit a wall

from sketch to symphony: how ai and a team of experts finished beethoven’s 10th

© Provided by The Independent To create something that Beethoven could have written, the AI ​​had to know all of the composer’s work (Hulton Fine Art Collection / Getty Images)

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

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

When it came to the 10th Symphony, however, the composer left little 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, the 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.

Assembling the team

In early 2019, I was contacted by Dr Matthias Roeder, the director of the Karajan Institute, an organisation in Salzburg, Austria, that aims to promote the links between music and technology.

He explained that he was putting together a team to complete Beethoven’s 10th Symphony in celebration of the 250th anniversary of the composer’s birth. Aware of my work on AI-generated art, he wanted to know if AI could help fill in the blanks left by Beethoven.

The challenge seemed daunting. To pull it off, AI would need to do something it had never done before. But I replied that I was ready to give it a try.

Roeder then formed a team that included the Austrian composer Walter Werzowa. Famous for writing Intel’s signature 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.

from sketch to symphony: how ai and a team of experts finished beethoven’s 10th

© Provided by The Independent A page of Beethoven's notes for his planned 10th Symphony (Beethoven House Museum , CC BY-SA)

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.

The project takes shape

In June 2019, the group gathered for a two-day workshop at Harvard’s music library. In a large room with a piano, a blackboard and a stack of Beethoven’s sketchbooks spanning most of his known works, we talked about how fragments could be turned into a complete piece of music and how AI could help solve this puzzle, while still remaining faithful to Beethoven’s process and vision.

The music experts in the room were eager to learn more about the sort of music AI had created in the past. I told them how AI had successfully generated music in the style of Bach. However, this was only a harmonisation of an inputted melody that sounded like Bach. It didn’t come close to what we needed to do: construct an entire symphony from a handful of phrases.

Meanwhile, the scientists in the room – myself included – wanted to learn about what sort of materials were available, and how the experts envisioned using them to complete the symphony.

At every point, Beethoven’s genius loomed, challenging us to do better. As the project evolved, the AI did as well

The task at hand eventually crystallised. We would need to use notes and completed compositions from Beethoven’s entire body of work – along with the available sketches from the 10th Symphony – to create something that Beethoven himself might have written.

This was a tremendous challenge. 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.

Piecing together Beethoven’s creative process

As the project progressed, the human side and the machine side of the collaboration evolved. Werzowa, Gotham, Levin, and Roeder deciphered and transcribed the sketches from the 10th Symphony, trying to understand Beethoven’s intentions. Using his completed symphonies as a template, they attempted to piece together the puzzle of where the fragments of sketches should go – which movement, which part of the movement.

They had to make decisions, such as determining whether a sketch indicated the starting point of a scherzo, which is a very lively part of the symphony, typically in the third movement. Or they might determine that a line of music was likely the basis of a fugue, which is a melody created by interweaving parts that all echo a central theme.

The AI side of the project – my side – found itself grappling with a range of challenging tasks.

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.

One of the music experts said the AI reminded him of an eager music student who practices every day, learns, and becomes better and better

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 harmonise it. The AI needed to learn how to bridge two sections of music together. And we realised 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 have done.

Passing the first big test

In November 2019, the team met in person again – this time at the Beethoven House Museum, in Bonn, 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.

from sketch to symphony: how ai and a team of experts finished beethoven’s 10th

© Provided by The Independent Journalists and musicians gather to hear a pianist play excerpts from the piece (Ahmed Elgammal/CC BY-SA)

A few days later, one of these AI-generated scores was played by a string quartet at 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.

Ready for the world

At every point, Beethoven’s genius loomed, challenging us to do better. As the project evolved, the AI did as well. Over the ensuing 18 months, we constructed and orchestrated two entire movements of more than 20 minutes apiece.

We anticipate some pushback to this work – those who will say that the arts should be off-limits from AI, and that AI has no business trying to replicate the human creative process. Yet when it comes to the arts, I see AI not as a replacement, but as a tool – one that opens doors for artists to express themselves in new ways.

This project would not have been possible without the expertise of human historians and musicians. It took an immense amount of work – and, yes, creative thinking – to accomplish this goal.

At one point, one of the music experts on the team said that the AI reminded him of an eager music student who practices every day, learns, and becomes better and better.

Now that student, having taken the baton from Beethoven, has presented the 10th Symphony to the world.

Ahmed Elgammal is a professor and the director of the Art & AI Lab at Rutgers University. This article first appeared on The Conversation.

From news to politics, travel to sport, culture to climate – The Independent has a host of free newsletters to suit your interests. To find the stories you want to read, and more, in your inbox, click here.

Internet Explorer Channel Network


LATEST NEWS

NEWS RELATED

Google Fi will soon offer end-to-end encrypted calls

If you’re a Google Fi subscriber, the next time you phone someone your call may be protected by end-to-end encryption. The MVNO will start rolling out support for the privacy-minded feature to Android phones in the coming weeks. Once it’s available on your device, it will kick in automatically anytime…

Read more: Google Fi will soon offer end-to-end encrypted calls

Recent Facebook Outage Baffles Many Users, DownDetector Reports

Facebook has undergone another round of outages just a few weeks after major social media apps experienced a brief downtime. According to DownDetector, many users raised their concerns about accessing the application’s news feed. Facebook Hit By Another Outage This Week (Photo : Joshua Hoehne from Unsplash)Facebook has experienced another…

Read more: Recent Facebook Outage Baffles Many Users, DownDetector Reports

Best cameras for photos and videos

© Provided by Space Best cameras: Image shows photographer stood on a mirrored lake pointing camera at mountains With so many different types of photographers out there, it’s hard for camera manufacturers to fit everything into one device. In fact, by doing so you rule out a vast majority of…

Read more: Best cameras for photos and videos

Didi expands, inDriver monetizes to rival Uber, Bolt in Africa

The on-demand transport space in Africa has evolved since San Francisco-based ride-hailing firm Uber first set up operations in South Africa in 2013, setting the stage for its foray across the continent while radically transforming the entire taxi industry. Almost a decade later, Africa’s taxi industry is now dominated by…

Read more: Didi expands, inDriver monetizes to rival Uber, Bolt in Africa

Anomalo launches with $33M Series A to automatically find issues in data sets

As companies gather ever-growing sets of data, finding issues with that data that could impact the viability of a machine learning model becomes increasingly important. Anomalo is putting machine learning to work to help solve the data viability issue automatically. Today the company announced a $33 million Series A investment…

Read more: Anomalo launches with $33M Series A to automatically find issues in data sets

Solo Brands CEO on IPO: Pandemic created a 'step up' for e-commerce success

Solo Brands made its public debut on the New York Stock Exchange. Solo Brands CEO John Merris joins Yahoo Finance Live to discuss.

Read more: Solo Brands CEO on IPO: Pandemic created a 'step up' for e-commerce success

U.S. troops in Taiwan, France seizes UK fishing boat, U.S. gender neutral passport

Yahoo Finance’s Akiko Fujita breaks down today’s top stories from around the world.

Read more: U.S. troops in Taiwan, France seizes UK fishing boat, U.S. gender neutral passport

iPhone SE 3: All the upgrades we want to see in Apple's next affordable iPhone

5G support, longer battery life and a newer processor are some of the features on our iPhone SE 3 wishlist.

Read more: iPhone SE 3: All the upgrades we want to see in Apple's next affordable iPhone

Google Pixel 6 Pro review: Finally, a proper iPhone rival

GlobalFoundries shares open flat on Nasdaq debut, valuing chipmaker at $26 bln

Game delays force French game maker Ubisoft to cut annual guidance

Redmi Note 11, Redmi Note 11 Pro and Redmi Note 11 Pro+ launched in China: Specs, camera and everything we know

Activision CEO seeks large pay cut, links it to gender-related goals

Lockheed, Masten, and ispace will talk going to the moon (and back) at TC Sessions: Space

Redmi Note 11 vs Redmi Note 10: Where Xiaomi's new affordable phone stands

Starbucks raises wages, Activision Blizzard CEO details pay cut, Third Point buys stake in Shell

OTHER NEWS