This AHRC-funded collaboration project creates a dialogue between performer-improviser David Dolan and composer-programmer Oded Ben-Tal. It will be the first time in the UK that an Artificial Intelligence (AI) computerised system performs duo improvisations in real time with a human, in the context of tonal/modal and extended tonality, in concert.

In this event, part of our ResearchWorks series, their performance will be followed by a discussion in which audiences can hear more about the technology and artistry behind this ground-breaking project. The audience is warmly invited to address questions to both artists and share thoughts about the experience.

How it works

The AI system that Ben-Tal is developing for this project relies on machine listening to analyse Dolan’s improvisations and generate (in real-time, and as an integral part of the performance) musical responses that relate to different aspects of his performance.

One of the pioneering aspects of David Dolan’s artistic practice and research relates to his work on improvising in tonal/modal/enlarged tonality musical environments. The system Ben-Tal is developing analyses the sound from the piano and makes inferences about the musical content aimed at shaping an appropriate response.

To make the system truly responsive and flexible, Ben-Tal is not programming in assumptions of music theory or stylistic conventions. Instead, imaginative use of cutting-edge machine listening technology, combined with algorithmic composition methods, opens possibilities for dialogue between the performer and the AI system.

The aim is for a system that adapts its response to what it “hears”. Most of the moment-to-moment sound production is handled by this interactive system. During the performance, Ben-Tal adjusts control parameters, thus shaping the computer’s larger-scale aspects of the dialogue.