Perception-Inspired Graph Convolution for Music Understanding Tasks
This work addresses music understanding problems like voice separation and composer identification for researchers and practitioners in music information retrieval, but it is incremental as it builds on existing graph network methods with domain-specific adaptations.
The authors tackled music understanding tasks by proposing MusGConv, a perception-inspired graph convolutional block for processing musical score data, which improved performance on three out of four tasks such as monophonic voice separation and harmonic analysis.
We propose a new graph convolutional block, called MusGConv, specifically designed for the efficient processing of musical score data and motivated by general perceptual principles. It focuses on two fundamental dimensions of music, pitch and rhythm, and considers both relative and absolute representations of these components. We evaluate our approach on four different musical understanding problems: monophonic voice separation, harmonic analysis, cadence detection, and composer identification which, in abstract terms, translate to different graph learning problems, namely, node classification, link prediction, and graph classification. Our experiments demonstrate that MusGConv improves the performance on three of the aforementioned tasks while being conceptually very simple and efficient. We interpret this as evidence that it is beneficial to include perception-informed processing of fundamental musical concepts when developing graph network applications on musical score data.