From Prediction to Collaboration: Interactive Symbolic Music Analysis

2026-07-15

AI Summary

This work addresses the limitations of existing automatic symbolic music analysis systems, which are typically confined to single-mode prediction and struggle to support interactive tasks such as local completion, correction, and iterative refinement. The paper proposes a unified framework that re-conceptualizes Roman numeral harmonic analysis from a purely predictive task into a collaborative, multimodal interactive foundation. By leveraging pretrained representations and integrating constrained sequence modeling, masked completion, and multi-granularity candidate generation, the approach achieves high analytical accuracy while substantially improving interaction efficiency. Evaluated on Dilemmadata—the largest heterogeneous benchmark—it attains strong baseline performance, effectively supports inference under partial annotations, and is complemented by a prototype interface enabling multi-level inspection and editing of analytical results.

Abstract

Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-score prediction, and therefore do not match the broader range of operations that arise in analysis workflows, including partial completion, local correction, and iterative refinement. As a result, there remains a gap between strong benchmark models and systems that can support interactive analytical use. We present a unified framework for symbolic Roman-numeral (RN) analysis that narrows this gap by combining strong predictive performance with direct support for constrained completion and revision. The method is designed to provide a practical trade-off between accuracy and interactive responsiveness by computing expensive pretrained representations once and reusing them during iterative refinement, making powerful pretrained models more amenable to interactive settings. It supports complete score analysis, targeted revision of existing labels, and inference of missing annotations from partial context through a shared modeling framework. Experiments on Dilemmadata, the largest and most heterogeneous benchmark of its kind, show that the proposed approach is a strong RN-analysis baseline while also supporting masked completion from partial labels. Together with a prototype interface for multi-level candidate inspection and editing, these results position automatic RN analysis not only as a prediction problem, but also as a foundation for future interactive tools for music analysis.

Problem

• symbolic music analysis
• interactive analysis
• Roman-numeral analysis
• constrained completion
• iterative refinement

Innovation

• interactive music analysis
• symbolic music analysis
• Roman numeral analysis
• constrained completion
• pretrained representation reuse