2026-06-28T20:20:11Zhttps://docta.ucm.es/rest/oai/request

oai:docta.ucm.es:20.500.14352/1143302025-09-16T17:41:03Zcom_20.500.14352_14col_20.500.14352_21

Optimizing feature straction for Symbolic Music Simonetta, Federico Llorens, Ana Llorens Martín, Ana Serrano, Martín García-Portugués, Eduardo Torrente, Álvaro Torrente Sánchez-Guisande, Álvaro José International Society for Music Information Retrieval This paper presents a comprehensive investigation of existing feature extraction tools for symbolic music and contrasts their performance to determine the set of features that best characterizes the musical style of a given music score. In this regard, we propose a novel feature extraction tool, named musif, and evaluate its efficacy on various repertoires and file formats, including MIDI, MusicXML, and **kern. Musif approximates existing tools such as jSymbolic and music21 in terms of computational efficiency while attempting to enhance the usability for custom feature development. The proposed tool also enhances classification accuracy when combined with other sets of features. We demonstrate the contribution of each set of features and the computational resources they require. Our findings indicate that the optimal tool for feature extraction is a combination of the best features from each tool rather than those of a single one. To facilitate future research in music information retrieval, we release the source code of the tool and benchmarks. 2025-01-14T18:08:43Z 2025-01-14T18:08:43Z 2025-01-14T18:08:43Z 2023 book part https://hdl.handle.net/20.500.14352/114330 XXXX-XXXX eng Didone: The Sources of Absolute Music (ERC Advanced Grant No. 788976) Optimizing feature straction for Symbolic Music / Fedrico Simonetta, Ana Llorens, Martín Serrano, Eduardo García-Portugué, Álvaro Torrente en : International Society for Music Information Retrieval. (2023). Proceedings of the 24th conference of the International Society for Music Information Retrieval, November 5-9, 2023, Milan, Italy (A. Sarti, Ed.). International Society for Music Information Retrieval. http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 International International Society for Music Information Retrieval