MusicGen-Chord: Advancing Music Generation through Chord Progressions and Interactive Web-UI

TL;DR

MusicGen-Chord enhances AI music generation by integrating chord progressions with textual and melodic inputs, enabling more musically coherent outputs, and is accessible via an interactive web interface.

Contribution

Introduces MusicGen-Chord, a novel extension of MusicGen that incorporates chord progression features into music generation models.

Findings

MusicGen-Chord effectively models chord progressions in generated music.

The web-based interface makes AI music creation accessible to users.

The model can generate musically coherent and diverse compositions.

Abstract

MusicGen is a music generation language model (LM) that can be conditioned on textual descriptions and melodic features. We introduce MusicGen-Chord, which extends this capability by incorporating chord progression features. This model modifies one-hot encoded melody chroma vectors into multi-hot encoded chord chroma vectors, enabling the generation of music that reflects both chord progressions and textual descriptions. Furthermore, we developed MusicGen-Remixer, an application utilizing MusicGen-Chord to generate remixes of input music conditioned on textual descriptions. Both models are integrated into Replicate's web-UI using cog, facilitating broad accessibility and user-friendly controllable interaction for creating and experiencing AI-generated music.