Skip to main content

Baidu's AI Composer translates famous artworks into melodies you can listen to

Baidu AI composer
An artificial intelligence algorithm created by China’s search giant, Baidu, is taking a crack at composing original music inspired by art. Dubbed the Baidu AI Composer, the algorithm uses image recognition software — supported by what the company calls “the world’s largest neural network” — that translates the content, tone, and mood of particular images into associated melodies.

In a promotional video, Baidu points out how paintings and pictures can evoke certain musical moods. A rainy day, for example, may evoke a melancholic melody. But these moods tend to be intuitive and aren’t always easy to explain — particularly not to an AI.

Recommended Videos

To do so, the company trained its AI to identify an image’s objects, colors, and setting, as each corresponds to certain emotions. Baidu then connected the composer to a database of musical compositions that are divided up into musical units and itemized by their mood. The system then reinterprets the elements of the image as a series of notes.

As impressive as the project sounds, Baidu only shares two of the AI composer’s simple piano compositions in the video. One is a light, dreamy melody that accompanies Van Gogh’s The Starry Night. The other is an energetic tune to a watercolor painting of galloping horses. Neither melody is particularly remarkable, though backing instruments — which Baidu seems to have added manually — do make the compositions seem more complete.

To be fair, Baidu suggests that its AI composer is still in the experimental phase and that it is currently on display at the Ullens Center for Contemporary Art in Beijing, reports The Stack. Perhaps the exhibition feature more elaborative compositions — otherwise we look forward to hearing the composer refine its talents.

Dyllan Furness
Former Digital Trends Contributor
Dyllan Furness is a freelance writer from Florida. He covers strange science and emerging tech for Digital Trends, focusing…
OpenAI’s new tool can spot fake AI images, but there’s a catch
OpenAI Dall-E 3 alpha test version image.

Images generated by artificial intelligence (AI) have been causing plenty of consternation in recent months, with people understandably worried that they could be used to spread misinformation and deceive the public. Now, ChatGPT maker OpenAI is apparently working on a tool that can detect AI-generated images with 99% accuracy.

According to Bloomberg, OpenAI’s tool is designed to root out user-made pictures created by its own Dall-E 3 image generator. Speaking at the Wall Street Journal’s Tech Live event, Mira Murati, chief technology officer at OpenAI, claimed the tool is “99% reliable.” While the tech is being tested internally, there’s no release date yet.

Read more
Spotify using AI to clone and translate podcasters’ voices
spotify app available in windows 10 store

Spotify has unveiled a remarkable new feature powered by artificial intelligence (AI) that translates a podcast into multiple languages using the same voices of those in the show.

It’s been made possible partly by OpenAI’s just-released voice generation technology that needs only a few seconds of listening to replicate a voice.

Read more
5 amazing AI features in Photoshop you can use now
A modern couple in a medieval scene that includes a flying Santa, crowns, and a flamingo gives an example of Photoshop AI.

Photoshop is one of the most versatile and powerful photo and image editing tools available, and Adobe is adding amazing new AI features to make it even better.

AI is also coming to Illustrator and Adobe Express. I took a look at how Adobe is expanding possibilities with AI and the results are impressive and easy.
AI image generation
Photoshop beta has AI image generation capabilities. Digital Trends

Read more