Deep Composer Classification Using Symbolic Representation
arXiv:2010.00823v219 citations
Originality Synthesis-oriented
AI Analysis
This work addresses composer classification for music analysis, but it is incremental as it applies existing deep learning methods to a specific domain.
The study trained deep neural networks to classify composers from symbolic music data, achieving an F1 score of 0.8333 for 13 classical composers on the MAESTRO dataset.
In this study, we train deep neural networks to classify composer on a symbolic domain. The model takes a two-channel two-dimensional input, i.e., onset and note activations of time-pitch representation, which is converted from MIDI recordings and performs a single-label classification. On the experiments conducted on MAESTRO dataset, we report an F1 value of 0.8333 for the classification of 13~classical composers.