Algorithms for Collaborative Harmonization

2025-08-28

AI Summary

This study addresses the core problem of harmonizing multiple melodic lines: “How to aggregate diverse harmonic suggestions into an optimal harmonic sequence that balances collective representativeness and musical coherence?” We propose the first collaborative harmony aggregation framework tailored for structured music language, innovatively integrating Kemeny ranking aggregation with majority voting to dynamically reconcile collective preference modeling and music-theoretic constraints. Through systematic experiments comparing multiple aggregation algorithms, we demonstrate that our method significantly outperforms baselines in both representation fidelity and harmonic coherence; specifically, the hybrid Kemeny–majority voting approach achieves the best overall performance. This work establishes an interpretable, computationally tractable theoretical framework and practical paradigm for collective intelligence in music AI.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Metareasoning and Metaheuristics
• Multiagent Systems: Mechanism Design

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We consider a specific scenario of text aggregation, in the realm of musical harmonization. Musical harmonization shares similarities with text aggregation, however the language of harmony is more structured than general text. Concretely, given a set of harmonization suggestions for a given musical melody, our interest lies in devising aggregation algorithms that yield an harmonization sequence that satisfies the following two key criteria: (1) an effective representation of the collective suggestions; and (2) an harmonization that is musically coherent. We present different algorithms for the aggregation of harmonies given by a group of agents and analyze their complexities. The results indicate that the Kemeny and plurality-based algorithms are most effective in assessing representation and maintaining musical coherence.

Problem

• Aggregate harmonization suggestions from multiple agents
• Produce musically coherent harmonization sequences
• Effectively represent collective input in harmonization

Innovation

• Kemeny algorithm for harmony aggregation
• Plurality-based method for musical coherence
• Structured harmonization from collective suggestions