The ability to automatically generate music that appropriately matches an arbitrary input track is a challenging task. We present a novel controllable system for generating single stems to accompany musical mixes of arbitrary length. At the core of our method are audio autoencoders that efficiently compress audio waveform samples into invertible latent representations, and a conditional latent diffusion model that takes as input the latent encoding of a mix and generates the latent encoding of a corresponding stem. To provide control over the timbre of generated samples, we introduce a technique to ground the latent space to a user-provided reference style during diffusion sampling. For further improving audio quality, we adapt classifier-free guidance to avoid distortions at high guidance strengths when generating an unbounded latent space. We train our model on a dataset of pairs of mixes and matching bass stems. Quantitative experiments demonstrate that, given an input mix, the proposed system can generate basslines with user-specified timbres. Our controllable conditional audio generation framework represents a significant step forward in creating generative AI tools to assist musicians in music production.

AI continuously generates two-bar rhythm patterns and corresponding basslines within this performance. Another AI model also keeps selecting loops that fit the rhythm and bassline. The DJ listens to the AI-generated parts and adjusts the sound of the drum machine and synthesizer on the spot. The DJ also controls the volume and audio effects of each track to build up the musical development. The DJ can also use turntables to mix records with AI-generated music.

After teasing her new single with lyrics scrawled in lipstick on Instagram, where she reigns supreme, Selena Gomez has released "Bad Liar." If it reminds you of the Talking Heads a lot more than you ever thought a Selena Gomez song would, that's on purpose. Songwriter Justin Tranter, who worked on the song with Gomez and songwriter Julia Michaels, explained how the Tina Weymouth bassline ended up on the track Variety. "Selena and Julia are Talking Heads-obsessed. So when we all got together in one room, Julia suggested, 'Why don't we just write over the bassline from "Psycho Killer?"'