Network representations of drum sequences for classification and generation

Gómez-Marín, Daniel; Jordà Puig, Sergi; Herrera, Perfecto

doi:http://dx.doi.org/10.3389/fcomp.2024.1476996

Network representations of drum sequences for classification and generation

Llicència

Citació

Gómez-Marín D, Jordà S, Herrera P. Network representations of drum sequences for classification and generation. Front Comput Sci. 2025 Jan 21;6:1476996. DOI: 10.3389/fcomp.2024.1476996

Resum

Complex networks have emerged as a powerful framework for understanding and analyzing musical compositions, revealing underlying structures and dynamics that may not be immediately apparent. This article explores the application of complex network representations to the study of symbolic drum sequences, a topic that has received limited attention in the literature. The proposed methodology involves encoding drum rhythms as directed, weighted complex networks, where nodes represent drum events, and edges capture the temporal succession of these events. This network-based representation allows for the analysis of similarities between different drumming styles, as well as the generation of novel drum patterns. Through a series of experiments, we demonstrate the effectiveness of this approach. First, we show that the complex network representation can accurately classify drum patterns into their respective musical styles, even with a limited number of training samples. Second, we present a generative model based on Markov chains operating on the network structure, which is able to produce new drum patterns that retain the essential features of the training data. Finally, we validate the perceptual relevance of the generated patterns through listening tests, where participants are unable to distinguish the generated patterns from the original ones, suggesting that the network-based representation effectively captures the underlying characteristics of different drumming styles. The findings of this study have significant implications for music research, genre classification, and generative music applications, highlighting the potential of complex networks to provide a transparent and elegant approach to the analysis and synthesis of rhythmic structures in music.