Learning and Blending Harmonies in the Context of a Melodic Harmonisation Assistant - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Learning and Blending Harmonies in the Context of a Melodic Harmonisation Assistant

(1) , (2) , (1) , (1) , (1)
1
2
Dimos Makris
  • Function : Author
  • PersonId : 992353
Asterios Zacharakis
  • Function : Author
  • PersonId : 1011947
Costas Tsougras
  • Function : Author
  • PersonId : 1011948
Emilios Cambouropoulos
  • Function : Author
  • PersonId : 1008274

Abstract

How can harmony in diverse idioms be represented in a machine learning system and how can learned harmonic descriptions of two musical idioms be blended to create new ones? This paper presents a creative melodic harmonisation assistant that employs statistical learning to learn harmonies from human annotated data in practically any style, blends the harmonies of two user-selected idioms and harmonises user-input melodies. To this end, the category theory algorithmic framework for conceptual blending is utilised for blending chord transition of the input idioms, to generate an extended harmonic idiom that incorporates a creative combination of the two input ones with additional harmonic material. The results indicate that by learning from the annotated data, the presented harmoniser is able to express the harmonic character of diverse idioms in a creative manner, while the blended harmonies extrapolate the two input idioms, creating novel harmonic concepts.
Fichier principal
Vignette du fichier
430537_1_En_46_Chapter.pdf (303.91 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01557609 , version 1 (06-07-2017)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Maximos Kaliakatsos-Papakostas, Dimos Makris, Asterios Zacharakis, Costas Tsougras, Emilios Cambouropoulos. Learning and Blending Harmonies in the Context of a Melodic Harmonisation Assistant. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.520-527, ⟨10.1007/978-3-319-44944-9_46⟩. ⟨hal-01557609⟩
84 View
108 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More