CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation

TL;DR

This paper introduces CompLex, an automatically constructed music theory lexicon that enhances AI music generation models by integrating comprehensive musical knowledge, significantly improving their performance and reliability.

Contribution

The paper presents a novel multi-agent algorithm for automatic music lexicon construction, enabling effective integration of music theory into AI models with minimal manual input.

Findings

CompLex improves performance of state-of-the-art text-to-music models

The lexicon contains 37,432 items derived from minimal input

CompLex is complete, accurate, non-redundant, and executable.

Abstract

Generative artificial intelligence in music has made significant strides, yet it still falls short of the substantial achievements seen in natural language processing, primarily due to the limited availability of music data. Knowledge-informed approaches have been shown to enhance the performance of music generation models, even when only a few pieces of musical knowledge are integrated. This paper seeks to leverage comprehensive music theory in AI-driven music generation tasks, such as algorithmic composition and style transfer, which traditionally require significant manual effort with existing techniques. We introduce a novel automatic music lexicon construction model that generates a lexicon, named CompLex, comprising 37,432 items derived from just 9 manually input category keywords and 5 sentence prompt templates. A new multi-agent algorithm is proposed to automatically detect and mitigate hallucinations. CompLex demonstrates impressive performance improvements across three state-of-the-art text-to-music generation models, encompassing both symbolic and audio-based methods. Furthermore, we evaluate CompLex in terms of completeness, accuracy, non-redundancy, and executability, confirming that it possesses the key characteristics of an effective lexicon.