Talking Drums: Generating drum grooves with neural networks
P. Hutchings. (2017)cite arxiv:1706.09558Comment: Proceedings of the First International Conference on Deep Learning and Music, Anchorage, US, May, 2017 (arXiv:1706.08675v1 cs.NE).
Abstract
Presented is a method of generating a full drum kit part for a provided
kick-drum sequence. A sequence to sequence neural network model used in natural
language translation was adopted to encode multiple musical styles and an
online survey was developed to test different techniques for sampling the
output of the softmax function. The strongest results were found using a
sampling technique that drew from the three most probable outputs at each
subdivision of the drum pattern but the consistency of output was found to be
heavily dependent on style.
Description
Talking Drums: Generating drum grooves with neural networks
cite arxiv:1706.09558Comment: Proceedings of the First International Conference on Deep Learning and Music, Anchorage, US, May, 2017 (arXiv:1706.08675v1 cs.NE)
%0 Generic
%1 hutchings2017talking
%A Hutchings, P.
%D 2017
%K music-generation neural-network
%T Talking Drums: Generating drum grooves with neural networks
%U http://arxiv.org/abs/1706.09558
%X Presented is a method of generating a full drum kit part for a provided
kick-drum sequence. A sequence to sequence neural network model used in natural
language translation was adopted to encode multiple musical styles and an
online survey was developed to test different techniques for sampling the
output of the softmax function. The strongest results were found using a
sampling technique that drew from the three most probable outputs at each
subdivision of the drum pattern but the consistency of output was found to be
heavily dependent on style.
@misc{hutchings2017talking,
abstract = {Presented is a method of generating a full drum kit part for a provided
kick-drum sequence. A sequence to sequence neural network model used in natural
language translation was adopted to encode multiple musical styles and an
online survey was developed to test different techniques for sampling the
output of the softmax function. The strongest results were found using a
sampling technique that drew from the three most probable outputs at each
subdivision of the drum pattern but the consistency of output was found to be
heavily dependent on style.},
added-at = {2017-12-18T12:45:49.000+0100},
author = {Hutchings, P.},
biburl = {https://www.bibsonomy.org/bibtex/25425861486b947aaf10f87296df5db08/ven7u},
description = {Talking Drums: Generating drum grooves with neural networks},
interhash = {b770d58b8aed65d743ad8c12dac4d997},
intrahash = {5425861486b947aaf10f87296df5db08},
keywords = {music-generation neural-network},
note = {cite arxiv:1706.09558Comment: Proceedings of the First International Conference on Deep Learning and Music, Anchorage, US, May, 2017 (arXiv:1706.08675v1 [cs.NE])},
timestamp = {2017-12-18T12:45:49.000+0100},
title = {Talking Drums: Generating drum grooves with neural networks},
url = {http://arxiv.org/abs/1706.09558},
year = 2017
}