The tool is based on machine learning.

Google (NASDAQ: GOOGL) recently published a research paper on its new AI tool, MusicLM, designed to create music. The tool is based on machine learning and is trained on vast amounts of data to learn how to recreate different forms of content, including music.

It works by allowing the user to enter a word or phrase that describes the type of music they want to create. The more detailed the description, the better the system can produce the desired music. (VOA Learning English)

An example instruction: “The main soundtrack of an arcade game. It is fast-paced and upbeat, with a catchy electric guitar riff. The music is repetitive and easy to remember, but with unexpected sounds…”

According to the team, the music produced by the system closely resembled the description provided saying it “produces high-quality music…over several minutes, while being faithful to the text conditioning signal.”

The researchers have not yet released the MusicLM models for public use but have released a dataset of 5,500 music-writing pairs prepared by professional musicians.

MusicLM has the potential to quickly and easily create high-quality music selections, but the researchers have also acknowledged the risks associated with machine learning, such as biases in the training data.

They plan to continue to study these risks and to improve the system by incorporating lyrics generation, text conditioning, and better voice and music quality.

Related Story:  An Investigation By Times Reveals The Dark Side Of Training Chatbots On Offensive Content

Photo by Adi Goldstein on Unsplash