A Context-Sensitive Approach to XAI in Music Performance

TL;DR

This paper proposes a context-sensitive framework called Explanatory Pragmatism (EP) for improving explainability in AI systems used in music performance, emphasizing audience-specific explanations and iterative refinement.

Contribution

It introduces a novel EP framework that tailors AI explanations to different audiences and contexts in music performance, addressing limitations of one-size-fits-all approaches.

Findings

EP enhances transparency in AI for music performance

Audience-specific explanations improve interpretability

Framework supports iterative refinement based on feedback

Abstract

The rapidly evolving field of Explainable Artificial Intelligence (XAI) has generated significant interest in developing methods to make AI systems more transparent and understandable. However, the problem of explainability cannot be exhaustively solved in the abstract, as there is no single approach that can be universally applied to generate adequate explanations for any given AI system, and this is especially true in the arts. In this position paper, we propose an Explanatory Pragmatism (EP) framework for XAI in music performance, emphasising the importance of context and audience in the development of explainability requirements. By tailoring explanations to specific audiences and continuously refining them based on feedback, EP offers a promising direction for enhancing the transparency and interpretability of AI systems in broad artistic applications and more specifically to music performance.