Real-time drum accompaniment using transformer architecture

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

doi:http://dx.doi.org/10.5281/zenodo.7088343

Real-time drum accompaniment using transformer architecture

License

Citation

Haki B, Nieto M, Pelinski T, Jordà S. Real-time drum accompaniment using transformer architecture. In: Proceedings of the 3rd Conference on AI Music Creativity (AIMC 2022); 2022 13-15 Sep; online. [s.l.]: AI Music Creativity; 2022. 10 p. DOI: 10.5281/zenodo.7088343

Abstract

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.