Non-chord Tone Identification Using Deep Neural Networks

Abstract

This paper addresses the problem of harmonic analysis by proposing a non-chord tone identification model using deep neural network (DNN). By identifying non-chord tones, the task of harmonic analysis is much simplified. Trained and tested on a dataset of 140 Bach chorales, an initial DNN was able to identify non-chord tones with F1-measure of 57.00%, using pitch-class information alone. By adding metric information, a small size contextual window, and fine-tuning DNN, the model's accuracy increased to a F1-measure of 72.19%. These results suggest that DNNs offer an innovative and promising approach to tackling the problem of non-chord tone identification, as well as harmonic analysis.