This futuristic Jukebox creates new music by your favorite artists by using a neural network.

Interesting EngineeringBy Derya Ozdemir


© Jukebox | OpenAI's Futuristic Jukebox Generates Music in Any Genre From Scratch


AI-generated music is a peculiar thing to think about for two reasons; 1) it is a fascinating new field, and 2) we don't really know where it is going and it feels uncanny. However, it is interesting both musically and commercially.
OpenAI has revealed new horizons on the subject by creating recreations of songs in the style of Pink Floyd, Ella Fitzgerald, 2Pac, and beyond.
The results are rather convincing; however, they also sound like drunk karaoke versions of your favorite tunes. 
Jukebox, the organization’s new music-generating system, was announced and detailed in a blog post and a new paper. According to their website, Jukebox is "a neural network that generates music, including rudimentary singing, as raw audio in a variety of genres and artistic styles."
They also released the code behind the Jukebox, along with a tool to explore the generated samples. They promise you a 12-minute read and 10-day listen. It's a sweet deal.

Compressing music into codes

The science behind the AI Jukebox is super interesting. In order to make it possible, they used raw audio to train the model, which spit out raw audio in return.
In order to get it to work, the researchers first used convolutional neural networks to encode and compress raw audio.  
After that, they used what they call a transformer to generate new compressed audio that was then upsampled to turn it back into raw audio. By doing so, the neural network generates songs that don't exist in the first place.
Provided with genre, artist, and lyrics as input, Jukebox outputs a new music sample produced from scratch.
This article was originally published by Interesting Engineering. 
Previous Post Next Post