We introduce a Maximum Entropy model able to capture the statistics of melodies in music. The model can be used to generate new melodies that emulate the style of a given musical corpus. Instead of using the n-body interactions of (n-1)-order Markov models, traditionally used in automatic music generation, we use a k-nearest neighbour model with pairwise interactions only. In that way, we keep the number of parameters low and avoid over-fitting problems typical of Markov models. We show that long-range musical phrases don't need to be explicitly enforced using high-order Markov interactions, but can instead emerge from multiple, competing, pairwise interactions. We validate our Maximum Entropy model by contrasting how much the generated sequences capture the style of the original corpus without plagiarizing it. To this end we use a data-compression approach to discriminate the levels of borrowing and innovation featured by the artificial sequences. Our modelling scheme outperforms both fixed-order and variable-order Markov models. This shows that, despite being based only on pairwise interactions, our scheme opens the possibility to generate musically sensible alterations of the original phrases, providing a way to generate innovation. © 2017 The Author(s).

Maximum entropy models capture melodic styles / Sakellariou, Jason; Tria, Francesca; Loreto, Vittorio; Pachet, Francois. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - 7:1(2017). [10.1038/s41598-017-08028-4]

Maximum entropy models capture melodic styles

Tria, Francesca
;
Loreto, Vittorio;
2017

Abstract

We introduce a Maximum Entropy model able to capture the statistics of melodies in music. The model can be used to generate new melodies that emulate the style of a given musical corpus. Instead of using the n-body interactions of (n-1)-order Markov models, traditionally used in automatic music generation, we use a k-nearest neighbour model with pairwise interactions only. In that way, we keep the number of parameters low and avoid over-fitting problems typical of Markov models. We show that long-range musical phrases don't need to be explicitly enforced using high-order Markov interactions, but can instead emerge from multiple, competing, pairwise interactions. We validate our Maximum Entropy model by contrasting how much the generated sequences capture the style of the original corpus without plagiarizing it. To this end we use a data-compression approach to discriminate the levels of borrowing and innovation featured by the artificial sequences. Our modelling scheme outperforms both fixed-order and variable-order Markov models. This shows that, despite being based only on pairwise interactions, our scheme opens the possibility to generate musically sensible alterations of the original phrases, providing a way to generate innovation. © 2017 The Author(s).
2017
Multidisciplinary
01 Pubblicazione su rivista::01a Articolo in rivista
Maximum entropy models capture melodic styles / Sakellariou, Jason; Tria, Francesca; Loreto, Vittorio; Pachet, Francois. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - 7:1(2017). [10.1038/s41598-017-08028-4]
File allegati a questo prodotto
File Dimensione Formato  
Sakellariou_Maximum_2017.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 2.63 MB
Formato Adobe PDF
2.63 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1072891
Citazioni
  • ???jsp.display-item.citation.pmc??? 5
  • Scopus 20
  • ???jsp.display-item.citation.isi??? 13
social impact