Publications

You can also find all these publications on my Zenodo directory.

Multimodal Music Information Processing and Retrieval: Survey and Future Challenges

Publication date: 2019-01-24 - Type: conferencepaper - Download - BibTex - DOI

Towards improving the performance in various music information processing tasks, recent studies exploit different modalities able to capture diverse aspects of music. Such modalities include audio recordings, symbolic music scores, midlevel representations, motion and gestural data, video recordings, editorial or cultural tags, lyrics and album cover arts. This paper critically reviews the various approaches adopted in Music Information Processing and Retrieval, and highlights how multimodal algorithms can help Music Computing applications. First, we categorize the related literature based on the application they address. Subsequently, we analyze existing information fusion approaches, and we conclude with the set of challenges that Music Information Retrieval and Sound and Music Computing research communities should focus in the next years.


Symbolic Music Similarity Through a Graph-Based Representation

Publication date: 2018-09-12 - Type: conferencepaper - Download - BibTex - DOI

In this work, a novel representation system for symbolic music is described. The proposed representation system is graph-based and could theoretically represent music both from a horizontal (contrapuntal) and from a vertical (harmonic) point of view, by keeping into account contextual and harmonic information. It could also include relationships between internal variations of motifs and themes. This is achieved by gradually simplifying the melodies and generating layers of reductions that include only the most important notes from a structural and harmonic viewpoint. This representation system has been tested in a music information retrieval task, namely melodic similarity, and compared to another system that performs the same task but does not consider any contextual or harmonic information, showing how the structural information is needed in order to find certain relations between musical pieces. Moreover, a new dataset consisting of more than 5000 leadsheets is presented, with additional meta-musical information taken from different web databases, including author, year of first performance, lyrics, genre and stylistic tags.


Enhanced Wikifonia Leadsheet Dataset

Publication date: 2018-11-01 - Download - BibTex - DOI

EWLD (Enhanced Wikifonia Leadsheet Dataset) is a music leadsheet dataset with more than 5.000 scores that comes with a lot of metadata about composers, works, lyrics and features. It is designed for musicological and research purposes.

A Public Domain version, named OpenEWLD, is available at https://framagit.org/sapo/OpenEWLD.

You can find an in-deep discussion in my Master Thesis.

 

Please, use the following paper as reference:

Simonetta, Federico, Carnovalini, Filippo, Orio, Nicola, & Rodà, Antonio. (2018). Symbolic Music Similarity Through a Graph-Based Representation. In Proceedings of the Audio Mostly 2018 on Sound in Immersion and Emotion (pp. 26:1–26:7). New York, NY, USA: ACM. http://doi.org/10.1145/3243274.3243301

Zenodo link: https://zenodo.org/record/2537059

 

My Master Thesis:

F. Simonetta, “Graph based representation of the music symbolic level. A music information retrieval application”, Università di Padova, 2018.

Zenodo link: https://zenodo.org/record/1476564

 


Graph based representation of the music symbolic level. A music information retrieval application

Publication date: 2018-04-09 - Type: thesis - Download - BibTex - DOI

In this work, a new music symbolic level representation system is described. It has been tested in two information retrieval tasks concerning similarity between segments of music and genre detection of a given segment. It could include both harmonic and contrapuntal information. Moreover, a new large dataset consisting of more than 5000 leadsheets is presented, with meta information taken from different web databases, including author information, year of first performance, lyrics, genre, etc.


Modellizzazione musicale tramite catene di Markov

Publication date: 2014-10-25 - Type: thesis - Download - BibTex - DOI

Questo lavoro ha avuto come obiettivo principale l'esplorazione del mondo della composizione algoritmica, in particolar modo di quel settore che opera con le catene di Markov, e lo sviluppo di un software che produca musica tramite catene di Markov allenate su brani preesistenti. Il primo capitolo delinea brevemente le linee generali di una possibile storia del pensiero logico-razionale in musica. Non vuole essere una trattazione esaustiva, ma, riguardando argomenti già ampiamente conosciuti dagli studiosi, si pone come una proposta di percorso tematico. Il secondo capitolo tratta, dopo una breve introduzione teorica, alcuni lavori scientifici cui si è venuti a conoscenza. Si è individuata nella letteratura qui trattata due grandi linee di lavoro: una che riguarda l'analisi musicale assistita dal calcolatore e una che tratta nuovi metodi per le pratiche musicali, siano esse improvvisate o meno. Molti dei lavori citati sono di recente data, a conferma che si tratta di un settore in via di evoluzione. L'ultimo capitolo, infine, tratta del laboratorio annesso alla presente trattazione, durante il quale si è sviluppato un piccolo software in Java capace di elaborare brani tramite catene di Markov; alcuni risultati potrebbero essere utilizzati anche al fine dell'analisi musicale.