Vincenzo Madaghiele
Pasquale Lisena
Raphael Troncy
2021-11-07
Sequence to Sequence (Seq2Seq) approaches have shown good performances in automatic music generation. We introduce MINGUS, a Transformer-based Seq2Seq architecture for modelling and generating monophonic jazz melodic lines.
MINGUS relies on two dedicated embedding models (respectively for pitch and duration) and exploits in prediction features such as chords (current and following), bass line, position inside the measure.
The obtained results are comparable with the state of the art of music generation with neural models, with particularly good performances on jazz music.
https://doi.org/10.5281/zenodo.5625684
oai:zenodo.org:5625684
ISMIR
https://zenodo.org/communities/ismir
https://doi.org/10.5281/zenodo.5625683
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
ISMIR 2021, International Society for Music Information Retrieval Conference, Online, November 7-12, 2021
MINGUS: Melodic Improvisation Neural Generator Using Seq2Seq
info:eu-repo/semantics/conferencePaper