Advancements in Human-AI Creative Interactions

The field of human-AI creative interactions is rapidly evolving, with a growing focus on longitudinal engagements and the development of more-than-human storytelling systems. Recent research has highlighted the complex dynamics that emerge between individuals and AI narrators over time, underscoring the potential of generative AI for storytelling while also raising critical questions about user agency and ethics. Another significant area of development is the investigation of emotional expression and perception in music performance, with studies exploring the influence of different performance settings and levels of expressiveness on emotional communication and audience engagement. Furthermore, the evaluation of generative models in music has become a topic of increasing interest, with researchers discussing the advantages and challenges of various approaches from musicological, engineering, and HCI perspectives. Noteworthy papers include: The paper 'More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI' which explored multi-generational experiences with a daily dream-crafting app and highlighted the complex dynamics that emerged between individuals and the AI narrator. The paper 'Exploring listeners' perceptions of AI-generated and human-composed music for functional emotional applications' which challenged the assumption that preference alone signals success in generative music systems and pointed toward a more careful design ethos that acknowledges the limits of replication and prioritizes human values.

Sources

More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI

Music interpretation and emotion perception: A computational and neurophysiological investigation

Exploring listeners' perceptions of AI-generated and human-composed music for functional emotional applications

The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing

A Statistics-Driven Differentiable Approach for Sound Texture Synthesis and Analysis

Improving AI-generated music with user-guided training

Survey on the Evaluation of Generative Models in Music

Built with on top of