Controllable Music Production with Diffusion Models and Guidance Gradients

no code implementations • 1 Nov 2023 • Mark Levy, Bruno Di Giorgi, Floris Weers, Angelos Katharopoulos, Tom Nickson

We demonstrate how conditional generation from diffusion models can be used to tackle a variety of realistic tasks in the production of music in 44. 1kHz stereo audio with sampling-time guidance.

Mel Spectrogram Inversion with Stable Pitch

no code implementations • 26 Aug 2022 • Bruno Di Giorgi, Mark Levy, Richard Sharp

We propose a new vocoder model that is specifically designed for music.

Downbeat Tracking with Tempo-Invariant Convolutional Neural Networks

no code implementations • 3 Feb 2021 • Bruno Di Giorgi, Matthias Mauch, Mark Levy

The human ability to track musical downbeats is robust to changes in tempo, and it extends to tempi never previously encountered.