Abstract:

This dissertation examines the generation of real-time symbolic drum accompaniments, with a particular focus on live improvisation contexts. While the research does occasionally focus on the audio domain, the majority of the research is centered on symbolic-to-symbolic systems. This dissertation addresses real-time drum accompaniment from multiple perspectives: (1) conceptual, where a target application is designed based on a set of specified requirements, (2) architectural, where specific generative models are designed and developed for the selected conceptual design, and (3) from a deployment aspect, where the conceptual design is realized and evaluated. Throughout this work, three accompaniment systems were developed and refined. As a secondary outcome, this research also produced NeuralMidiFx, a toolkit designed to streamline the integration of generative neural networks into VST plugins. Furthermore, two novel datasets, TapTamDrum and El Bongosero, were collected to support future research in areas ranging from rhythm perception to music generation.