SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning

TL;DR

SonicVerse is a multi-task learning model that generates detailed music captions by integrating music feature detection, enhancing descriptive accuracy for both short and long music pieces.

Contribution

Introduces a novel projection-based multi-task architecture that combines captioning with auxiliary music feature detection, improving descriptive quality in music AI.

Findings

Enhanced caption detail and accuracy with feature integration

Effective chaining for long music descriptions using LLMs

Extended MusicBench dataset with music feature annotations

Abstract

Detailed captions that accurately reflect the characteristics of a music piece can enrich music databases and drive forward research in music AI. This paper introduces a multi-task music captioning model, SonicVerse, that integrates caption generation with auxiliary music feature detection tasks such as key detection, vocals detection, and more, so as to directly capture both low-level acoustic details as well as high-level musical attributes. The key contribution is a projection-based architecture that transforms audio input into language tokens, while simultaneously detecting music features through dedicated auxiliary heads. The outputs of these heads are also projected into language tokens, to enhance the captioning input. This framework not only produces rich, descriptive captions for short music fragments but also directly enables the generation of detailed time-informed descriptions for longer music pieces, by chaining the outputs using a large-language model. To train the model, we extended the MusicBench dataset by annotating it with music features using MIRFLEX, a modular music feature extractor, resulting in paired audio, captions and music feature data. Experimental results show that incorporating features in this way improves the quality and detail of the generated captions.