Towards human-computer music interaction : evaluation of an affectively-driven music generator via galvanic skin response measures

Daly, I; Malik, A; Weaver, J; Hwang, F; Nasuto, SJ; Williams, DAH; Kirke, A; Miranda, E

Abstract

An affectively driven music generation system is described and evaluated. The system is developed for the intended eventual use in human-computer interaction systems such as brain-computer music interfaces. It is evaluated for its ability to induce changes in a listeners affective state. The affectively-driven algorithmic composition system was used to generate a stimulus set covering 9 discrete sectors of a 2-dimensional affective space by means of a 16 channel feedforward artificial neural network. This system was used to generate 90 short pieces of music with specific affective intentions, 10 stimuli for each of the 9 sectors in the affective space. These pieces were played to 20 healthy participants, and it was observed that the music generation system induced the intended affective states in the participants. This is further verified by inspecting the galvanic skin response recorded from participants.

Citation

Daly, I., Malik, A., Weaver, J., Hwang, F., Nasuto, S., Williams, D., …Miranda, E. Towards human-computer music interaction : evaluation of an affectively-driven music generator via galvanic skin response measures. Presented at 7th Computer Science and Electronic Engineering Conference, University of Essex, Colchester, UK

• Presentation Conference Type: Other
• Conference Name: 7th Computer Science and Electronic Engineering Conference
• Conference Location: University of Essex, Colchester, UK
• End Date: Sep 25, 2015
• Online Publication Date: Nov 23, 2015
• Publication Date: Nov 23, 2015
• Deposit Date: Dec 12, 2019
• Book Title: 2015 7th Computer Science and Electronic Engineering Conference (CEEC)
• ISBN: 9781467394819
• DOI: https://doi.org/10.1109/ceec.2015.7332705
• Publisher URL: https://doi.org/10.1109/ceec.2015.7332705
• Related Public URLs: https://ceec.uk/ceec15/
• Additional Information: Event Type : Conference; Funders : Engineering and Physical Sciences Research Council (EPSRC); Grant Number: EP/J003077/1; Grant Number: EP/J002135/1