Word Representation for Rhythms
Machine Learning
2020-09-04 v4 Computation and Language
Information Retrieval
Abstract
This paper proposes a word representation strategy for rhythm patterns. Using 1034 pieces of Nottingham Dataset, a rhythm word dictionary whose size is 450 (without control tokens) is generated. BERT model is created to explore syntactic potentials of rhythm words. Our model is able to find overall music structures and cluster different meters. In a larger scheme, a think mode - music as language - is proposed for systematic considerations.
Cite
@article{arxiv.2007.10610,
title = {Word Representation for Rhythms},
author = {Tongyu Lu and Lyucheng Yan and Gus Xia},
journal= {arXiv preprint arXiv:2007.10610},
year = {2020}
}
Comments
Construction of this paper is ill. The first author decides that this paper needs thorough rewriting and more experiments should be done