Gioti, Artemi-Maria. 2021. "A Compositional Exploration of Computational Aesthetic Evaluation and AI Bias." In Proceedings of the 2021 International Conference on New Interfaces for Musical Expression. [PubPub link]
ABSTRACT: This paper describes a subversive compositional approach to machine learning, focused on the exploration of AI bias and computational aesthetic evaluation. In Bias, for bass clarinet and Interactive Music System, a computer music system using two Neural Networks trained to develop "aesthetic bias" interacts with the musician by evaluating the sound input based on its "subjective" aesthetic judgments. The composition problematizes the discrepancies between the concepts of error and accuracy, associated with supervised machine learning, and aesthetic judgments as inherently subjective and intangible. The methods used in the compositional process are discussed with respect to the objective of balancing the trade-off between musical authorship and interpretative freedom in interactive musical works.
Gioti, Artemi-Maria. 2021. "Converge/Diverge: Collaborative Emergence in a Composition for Piano, Double Bass and Interactive Music System." In Proceedings of the 2021 International Computer Music Conference. [pdf]
ABSTRACT: This paper describes a composition for piano, double bass and interactive music system exploring the concepts of collaborative emergence and joint agency. In Converge/Diverge, the computer monitors the degree of timbral similarity between the two audio inputs (piano and double bass), identifies instances of "convergence" and "divergence" between them and responds accordingly. In addition to responding to the interaction between the two musicians, the interactive music system can act proactively, by initiating two additional interaction scenarios: "compete" and "cooperate". During the performance, the intentions of human and non-human agents are being continuously negotiated and adapted to changing group dynamics, leading to varied musical outcomes. The compositional methods used in the creation of the piece are discussed with respect to the conceptual and practical challenges posed by the concept of interactive musical works.
Gioti, Artemi-Maria. 2021. "Artificial Intelligence For Music Composition." In Handbook of Artificial Intelligence for Music: Foundations, Advanced Approaches, and Developments for Creativity, edited by Eduardo Reck Miranda. Berlin, Heidelberg: Springer. https://www.springer.com/gp/book/9783030721152.
Elblaus, Ludvig, and Gerhard Eckel. 2020. "Utruchirp: An Impulse Response Measurement and Auralisation Tool Developed for Artistic Practice." In Proccedings of Audio Mostly 2020, 61-68, Graz. [pdf] [video]
ABSTRACT: This paper presents the utruchirp software, a tool for measuring impulse responses and modelling room acoustics in real time through auralisation based on convolution using those responses. utruchirp is the result of concerns and needs emerging from the authors’ ongoing artistic practice, exploring room scale acoustic feedback as material for live performance, installations, and fixed media pieces as utrumque. The paper provides the technical and, more importantly, the artistic details of the development of utruchirp and its features, highlighting those that are the direct result of insights from artistic work: Monitoring of all stages of measuring and signal processing, auralisations of the measurements from within the measurement process, and integrated round trip delay estimation. Finally, it points out future directions and features that are to be explored next, with an invitation for collaborative efforts, aiming to bring the sensibilities of musical instruments to our measurement tools.
Elblaus, Ludvig, and Gerhard Eckel. 2020. "Acoustic Modelling as a Strategy for Composing Site-Specific Music." In Proceedings of Audio Mostly 2020, 69-76, Graz. [pdf] [video]
ABSTRACT: This paper describes two site-specific musical compositions, focusing on how modelling was used in their respective composition processes. Primarily, the acoustics of the sites were modelled to aid in the preparation and composition of the pieces. From this we propose the general use of modelling as a way to work with the concept of site. But the idea of formulating a model is also applicable more widely in the work described and this is discussed with the two pieces as starting points. Both pieces use acoustic room scale feedback as their only source of sound, so the impact of the room, speakers and microphones used is immense. The first piece, Rundgång, is a commission for the GRM Acousmonium. The second piece, Clockwork, is a public installation that will also be the site of a performance, combining the installation with live interventions. Clockwork will also employ modelling as a component of the piece itself, and include a remote performer and a remote audience. We suggest that there are possibilities to employ compositional strategies to embrace these kinds of hybrid presence situations by composing for many vantage points.
Gioti, Artemi-Maria. 2020. "From Artificial to Extended Intelligence in Music Composition". Organised Sound, 25 (1): 25-32. https://doi.org/10.1017/S1355771819000438
ABSTRACT: This article explores the relationship and disparities between human and computational creativity by addressing the following questions: How well are computational creativity systems currently performing at creative tasks? Could computers outperform human composers? And, if not, is computational creativity a utopia? Automatic composition systems are examined with respect to Boden's three criteria of creativity (novelty, surprise and value), as well as their assumptions about the nature of creativity. As an alternative to a competitive relationship between human and computational creativity, the article proposes the concept of a distributed human-computer co-creativity, in which computational creativity extends - rather than replaces - human creativity, by expanding the space of creative possibilities.
Gioti, Artemi-Maria. 2019. "Imitation Game: Real-Time Decision-making in an Interactive Composition for Human and Robotic Percussionist". In Proceedings of the 2019 International Computer Music Conference, New York. [pdf]
ABSTRACT: This paper describes an interactive composition for human and robotic percussionist exploring decision-making processes in the context of composed interaction scenarios. The composition is based on a dynamic form, shaped by decisions made by the musician and the robotic percussionist in real-time. Using a Neural Network trained to recognize different instruments and playing techniques, the robotic percussionist makes long-term decisions based on metrics of musical contrast. Similarly, the musician interprets a non-linear score, consisting of algorithmic instructions, which enables him/her to interact with the robotic percussionist in real-time. The paper describes various components of the system, including the auditory processing and decision-making stage and introduces a framework for artistic experimentation borrowing evaluation methods from human-computer improvisation.