MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models

TL;DR

MuChoMusic is a comprehensive benchmark designed to evaluate the music understanding capabilities of multimodal audio-language models, highlighting current limitations and guiding future improvements in the field.

Contribution

It introduces a new, validated benchmark with diverse questions to assess multimodal models' music understanding and analyzes existing models' performance and shortcomings.

Findings

Models often rely too heavily on language modality.

Current models struggle with fundamental musical concepts.

The benchmark reveals significant room for improvement in multimodal integration.

Abstract

Multimodal models that jointly process audio and language hold great promise in audio understanding and are increasingly being adopted in the music domain. By allowing users to query via text and obtain information about a given audio input, these models have the potential to enable a variety of music understanding tasks via language-based interfaces. However, their evaluation poses considerable challenges, and it remains unclear how to effectively assess their ability to correctly interpret music-related inputs with current methods. Motivated by this, we introduce MuChoMusic, a benchmark for evaluating music understanding in multimodal language models focused on audio. MuChoMusic comprises 1,187 multiple-choice questions, all validated by human annotators, on 644 music tracks sourced from two publicly available music datasets, and covering a wide variety of genres. Questions in the benchmark are crafted to assess knowledge and reasoning abilities across several dimensions that cover fundamental musical concepts and their relation to cultural and functional contexts. Through the holistic analysis afforded by the benchmark, we evaluate five open-source models and identify several pitfalls, including an over-reliance on the language modality, pointing to a need for better multimodal integration. Data and code are open-sourced.