AnalysisGNN: Unified Music Analysis with Graph Neural Networks
This addresses the need for more robust and comprehensive music analysis tools for researchers and practitioners in computational musicology, though it appears incremental as it builds on existing GNN techniques with specific adaptations.
The paper tackles the problem of fragmented computational approaches to music analysis by introducing AnalysisGNN, a unified graph neural network framework that integrates heterogeneously annotated symbolic datasets, achieving performance comparable to traditional methods while showing increased resilience to domain shifts and annotation inconsistencies.
Recent years have seen a boom in computational approaches to music analysis, yet each one is typically tailored to a specific analytical domain. In this work, we introduce AnalysisGNN, a novel graph neural network framework that leverages a data-shuffling strategy with a custom weighted multi-task loss and logit fusion between task-specific classifiers to integrate heterogeneously annotated symbolic datasets for comprehensive score analysis. We further integrate a Non-Chord-Tone prediction module, which identifies and excludes passing and non-functional notes from all tasks, thereby improving the consistency of label signals. Experimental evaluations demonstrate that AnalysisGNN achieves performance comparable to traditional static-dataset approaches, while showing increased resilience to domain shifts and annotation inconsistencies across multiple heterogeneous corpora.