Convolutional Composer Classification
This work addresses composer classification for musicology, but it is incremental as it builds on existing datasets and compares to prior smaller studies.
The paper tackles the problem of attributing composers to musical scores by introducing end-to-end learnable convolutional architectures, achieving results comparable to previous studies on a corpus of 2,500 scores from the KernScores collection.
This paper investigates end-to-end learnable models for attributing composers to musical scores. We introduce several pooled, convolutional architectures for this task and draw connections between our approach and classical learning approaches based on global and n-gram features. We evaluate models on a corpus of 2,500 scores from the KernScores collection, authored by a variety of composers spanning the Renaissance era to the early 20th century. This corpus has substantial overlap with the corpora used in several previous, smaller studies; we compare our results on subsets of the corpus to these previous works.