Learning and Evaluating Musical Features with Deep Autoencoders
Sound
2017-06-19 v2 Artificial Intelligence
Abstract
In this work we describe and evaluate methods to learn musical embeddings. Each embedding is a vector that represents four contiguous beats of music and is derived from a symbolic representation. We consider autoencoding-based methods including denoising autoencoders, and context reconstruction, and evaluate the resulting embeddings on a forward prediction and a classification task.
Cite
@article{arxiv.1706.04486,
title = {Learning and Evaluating Musical Features with Deep Autoencoders},
author = {Mason Bretan and Sageev Oore and Doug Eck and Larry Heck},
journal= {arXiv preprint arXiv:1706.04486},
year = {2017}
}