Conference paper Open Access

Real-Time Drum Accompaniment Using Transformer Architecture

Haki, Behzad; Nieto, Marina; Pelinski, Teresa; Jordà, Sergi

This paper presents a real-time drum generation system capable of accompanying a human instrumentalist. The drum generation model is a transformer encoder trained to predict a short drum pattern given a reduced rhythmic representation. We demonstrate that with certain design considerations, the short drum pattern generator can be used as a real-time accompaniment in musical sessions lasting much longer than the duration of the training samples. A discussion on the potentials, limitations and possible future continuations of this work is provided.

Files (5.7 MB)
Name Size
Haki_2022__Real-Time_Drum_Accompaniment_Using_Transformer_Architecture.pdf
md5:3621c0e41f5406aa2d36c211c55a112d
5.7 MB Download
48
48
views
downloads
All versions This version
Views 4848
Downloads 4848
Data volume 274.8 MB274.8 MB
Unique views 4444
Unique downloads 4747

Share

Cite as