Modeling Musical Onset Probabilities via Neural Distribution Learning
Sound
2020-02-11 v1 Machine Learning
Audio and Speech Processing
Abstract
Musical onset detection can be formulated as a time-to-event (TTE) or time-since-event (TSE) prediction task by defining music as a sequence of onset events. Here we propose a novel method to model the probability of onsets by introducing a sequential density prediction model. The proposed model estimates TTE & TSE distributions from mel-spectrograms using convolutional neural networks (CNNs) as a density predictor. We evaluate our model on the Bock dataset show-ing comparable results to previous deep-learning models.
Cite
@article{arxiv.2002.03559,
title = {Modeling Musical Onset Probabilities via Neural Distribution Learning},
author = {Jaesung Huh and Egil Martinsson and Adrian Kim and Jung-Woo Ha},
journal= {arXiv preprint arXiv:2002.03559},
year = {2020}
}
Comments
2 pages, 2 figures, 2 tables