MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models

TL;DR

MeLFusion is a diffusion-based model that synthesizes music from combined textual and visual cues, introducing a novel visual synapse mechanism and a new dataset and evaluation metric for this task.

Contribution

It presents a new multimodal music synthesis model with a visual synapse, along with a dataset and evaluation metric, advancing the integration of visual information in music generation.

Findings

Adding visual cues improves music quality significantly.

The model achieves up to 67.98% improvement on FAD score.

The approach demonstrates the effectiveness of multimodal conditioning in music synthesis.

Abstract

Music is a universal language that can communicate emotions and feelings. It forms an essential part of the whole spectrum of creative media, ranging from movies to social media posts. Machine learning models that can synthesize music are predominantly conditioned on textual descriptions of it. Inspired by how musicians compose music not just from a movie script, but also through visualizations, we propose MeLFusion, a model that can effectively use cues from a textual description and the corresponding image to synthesize music. MeLFusion is a text-to-music diffusion model with a novel "visual synapse", which effectively infuses the semantics from the visual modality into the generated music. To facilitate research in this area, we introduce a new dataset MeLBench, and propose a new evaluation metric IMSM. Our exhaustive experimental evaluation suggests that adding visual information to the music synthesis pipeline significantly improves the quality of generated music, measured both objectively and subjectively, with a relative gain of up to 67.98% on the FAD score. We hope that our work will gather attention to this pragmatic, yet relatively under-explored research area.