Home / Technology / Dynascore’s AI Music Engine writes tracks to match your videos

Dynascore’s AI Music Engine writes tracks to match your videos



They did not have much trouble finding musicians to compose songs; Peter had deep connections to the music scene in New York, and people like Jarret needed something to occupy their time.

With Jarrett and a small group of furloughed Broadway composers, arranger and orchestrators writing the music, Dynascore’s technical team stumbled into a best-case scenario when it came to internal talent. Who better to write pieces that evoke visual drama than those who have already paid to do it every night?

The human problem

The golden ears of human composers are truly the key to Dynascore̵

7;s ultimate success. The historical problem with AI-based, or “algorithmically composed” music, according to Saatchi, was that it mostly tried to teach software instruments to write music from scratch, rather than interpreting pieces that had already been written.

“Making music that actually resonates with people is a human problem, so you have to start with the people,” says Saatchi. “AI is the compressor for humans.”

In the early days of Dynascore, Saatchi and his team worked to develop a way to break down original music and out-of-copyright classics (think Grieg’s “Hall of the Mountain King”) into segments they call “morphones.” They taught AI a song and asked it to compose something similar using the morphs of the original song as a guide. Afterwards, they asked the musicians to criticize AI’s composition.

Making music fit perfectly in a video is not as easy as chopping up existing songs in predictable ways. Organic transitions require a more thorough understanding of key, rhythm and intensity, among other musical markers. As such, morphons not only indicate the speed and key of a song. They also indicate various other tonal and musical characteristics, all of which let AI know which types of musical Lego blocks snap together in which ways.

After developing the morphon system, the team wanted to feed the AI ​​songs and have them compose them again. It took a while before it was musically literate enough to make good choices.

“AI would compose a piece, and the musicians would go, ‘It was bad,'” Saatchi says, chuckling at the simplicity of the test. “It gets the feedback and it learns from it, and it gets to the point where it suddenly creates coherent compositions.”

AI soon became smart enough to fit transitions, fades, pauses, and other user-dictated timing shifts into each tune it wrote. The version of Dynascore that I witnessed reshaping the Moonlight Sonata was born.

Take a load off

Dynascore’s performance represents a dramatic improvement over what has historically been a cumbersome workflow.

“When you work as an editor or filmmaker, you spend so much time with the music, because you have to make it fit frame by frame,” says DiGiovanna, who has worked on everything from feature films to TV commercials, “With Dynascore you can do it on the go. ”

Watch a demo of how Dynascore handles scene transitions.

A tool that enables dynamic musical composition is especially useful when working on commercial projects where there may be a need to cut certain objects. DiGiovanna gives an example of a director who needs a bag removed from an ad he created.

“You have to remove five seconds of video, and now the end of the song does not work, the transition to the next song does not work,” he says, “That’s when Dynascore is going to save me a lot of time.”


Source link