Skip to main content

Watch: IBM uses artificial intelligence to make music with Phony Ppl

When you look at the artists behind your favorite songs, you never see “Chance the Rapper featuring Macbook Pro.” That’s because the computer’s role in making music is purely utilitarian, not collaborative. IBM is looking to change that by adding artificial intelligence into the mix with Watson Beat, an AI application that aims to turn your sounds and moods into beautiful music.

To get the process started, you insert a MIDI instrument into the application which turns the notes you play into digital information. You then play for 10 seconds, and Watson Beat will begin analyzing your melody. The program then presents you with six moods to choose from: amped, dark, romantic, angst, spooky, and worldly. Unlike song recommendation algorithms from Spotify and Pandora, Beat understands music theory and emotional responses to music, and also has the ability to break down the minute details of a song thanks to advanced IBM programming. So instead of recommending a song like a music streaming service, Watson Beat actually creates a new one.

To see Beat in action, Digital Trends traveled to The Spacement studios in Brooklyn, NY where multi-talented R&B group Phony PPL worked with the new app. The group was fresh off an eight-show residency at Blue Note jazz club, where legends like Ray Charles and Dizzy Gillespie once graced the stage on a regular basis. The group was almost immediately wowed by the program, amazed at how quickly it responded to their basic musical input to help spark creativity in the studio.

The prospect of a computer program making music with minimal instructions got Phony PPL lead singer Elbee Thrie wondering if Watson Beat might one day help musicians better define the ineffable when it comes to emotional musical responses. “I think it would be cool if Watson had the ability to have the algorithm for modes not defined by human emotions,” Thrie said. “You can sit with [the audio] and be like: ‘how am I feeling? I’m not sad, this is another range of emotions we don’t have words for in the dictionary.'” Thrie is hoping one day Watson can help flesh out those emotions, possibly even as custom presets.

As you can see in the video above, Watson Beat is far from a novelty, and is actually indicative of a growing trend of AI-created art. “This will be the first year in which AI-generated art will achieve commercial success. An artist will use an AI-created element, like a song melody, in a piece of work that achieves mainstream recognition,”  Nvidia’s Bryan Catanzaro, Vice President, Applied Deep Learning Research, told Digital Trends at this year’s Consumer Electronics Show (CES).

Watson Beat is currently only available to certain developers and artists. But IBM tells Digital Trends the app will be available to anyone by the end of the year. Before you know it, your favorite artist may be collaborating with Watson instead of Rihanna.

Check out the video of our time with Phony Ppl and IBM’s Watson Beat above.

Editors' Recommendations

Keith Nelson Jr.
Former Digital Trends Contributor
Keith Nelson Jr is a music/tech journalist making big pictures by connecting dots. Born and raised in Brooklyn, NY he…
Animal-A.I. Olympics will test bots against the latest animal intelligence tests
animal ai olympics challenge animalolympics getty 1

A few months back, we wrote about the Animal-A.I. Olympics, a then in-development competition which aimed to test top artificial intelligence agents by putting them through cognition tests designed for animals. This was intended to be open to anyone who wanted to create an A.I. they thought would be able to pass a battery of tests, all meant to measure some aspect of bot intelligence. Jump forward to the present day, and the contest has officially launched -- with its creators releasing Version 1.0 of the test environment, and announcing the official rules for entrants, increased prize money, and other crucial information.

“For prizes, we now have $32,000 equivalent value, with $20,000 total in cash and travel reimbursement for the top three entries and the most biologically plausible entry,” Matthew Crosby, a postdoctoral A.I. researcher working on the project, told Digital Trends. “We are also giving out $10,000 worth of AWS credits half-way through -- $500 to each of the top 20 entries -- that can be used during the second half of the competition.”

Read more
A learning bias found in kids could help make A.I. technology better
How to take kids photos

The theory behind machine learning tools that are like neural networks is that they function and, more specifically, learn in a similar way to the human brain. Just as we discover the world through trial and error, so too does modern artificial intelligence. In practice, however, things are a bit different. There are aspects of childhood learning that machines can’t replicate -- and they’re one of the things which, in many domains, make humans superior learners.

Researchers at New York University are working to change that. Researchers Kanishk Gandhi and Brenden Lake have explored how something called “mutual exclusivity bias,” which is present in kids, could help make A.I. better when it comes to learning tasks like understanding language.

Read more
How IBM’s cutting-edge A.I. put a losing soccer team on a winning streak
A soccer ball in a net.

How One English Football Club Scores Points with AI

If you’ve seen the 2011 movie Moneyball, or read the brilliant Michael Lewis book it’s based on, you will be familiar with the way that data and more than a pinch of clever math can be used to create a winning sports team out of seemingly non-promising components. But what if you were to go one step further and apply the computing power of IBM’s Watson artificial intelligence? As it turns out, the A.I., which once beat human players at Jeopardy, is equally at home improving the odds of an underdog sports team.

Read more