Conference paper Open Access

MINGUS: Melodic Improvisation Neural Generator Using Seq2Seq

Vincenzo Madaghiele; Pasquale Lisena; Raphael Troncy

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.
Files (662.9 kB)
Name Size
000051.pdf
md5:9631a92ee4819cb657d925a358fb1c50
662.9 kB Download
88
62
views
downloads
All versions This version
Views 8888
Downloads 6262
Data volume 41.1 MB41.1 MB
Unique views 8282
Unique downloads 5454

Share

Cite as