论文信息 - Deep Composer Classification Using Symbolic Representation

Deep Composer Classification Using Symbolic Representation

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.

[1] Akshay Smit,et al. Analysis and Classification of Symbolic Western Classical Music by Composer , 2019 .

[2] Colin Raffel,et al. Onsets and Frames: Dual-Objective Piano Transcription , 2017, ISMIR.

[3] Gianluca Micchi,et al. A neural network for composer classification , 2018 .

[4] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5] Douglas Eck,et al. Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset , 2018, ICLR.

[6] Vlado Keselj,et al. n-gram-based approach to composer recognition , 2008 .