New AI bassline generator by Sony can create accompaniments that match the “style and tone” of your input music
Should human bassists be afraid?
Credit: Andrey Suslov/Getty Images
A team of researchers from Sony Computer Science Laboratories (Sony CSL) have developed a new AI model that focuses solely on bass accompaniments.
According to a paper posted on the arXiv preprint server, Marco Pasini, Stefan Lattner, and Maarten Grachten at CSL have created a Diffusion model capable of producing realistic basslines that match the style and tone of existing music pieces.
- READ MORE: Behringer and Roland dominate in new world map showing most popular synth brands by country
“At Sony CSL, we aim to assist music artists and producers in their workflow by providing AI-powered tools,” Lattner tells Tech Xplore. “However, we have noticed that the most common approach of AI tools generating complete musical pieces from scratch (often controlled only by text input) is not very interesting to artists.”
Given that existing music generative tools often fail to take into account users’ unique preferences and style, the team wanted to come up with something more tailored and specific to the individual.
“Artists require tools that can adjust to their unique style and can be utilised at any point in their music production process,” Lattner said. “Therefore, a generative music tool should be able to analyse and take into account any intermediate creation of the artist when proposing new sounds.”
The new model is thus designed to generate basslines that complement existing material, regardless of the elements it contains: “Our system can process any type of musical mix that contains one or more sources, such as vocals, guitar, etc,” Lattner explained.
In addition, the tool is capable of generating “coherent basslines of any length”. Users can also control the timbre and playing style of the generated bass by providing a reference audio file.
Researchers added that similar models could be created for drums, piano, guitar, strings, and sound effects parts in the future.
“More broadly, we plan to collaborate directly with artists and composers to refine further and validate these AI accompaniment tools to best enhance their creative needs,” said Lattner.
