🤖 AI Summary
This study addresses the central challenge of how artificial intelligence can approximate human emotional expression in expressive piano performance rendering by proposing and implementing the RenCon 2025 international competition framework. The framework innovatively integrates a two-stage evaluation protocol combining online preliminary assessment with live, real-time rendering, engaging nine global teams employing diverse methodologies spanning generative AI, music information retrieval, real-time audio synthesis, and human-computer interaction. Beyond revitalizing and refining the evaluation paradigm for expressive performance rendering—marking the first instance of coordinated online-offline assessment—the initiative establishes a standardized benchmark for music generation research. It systematically demonstrates that while current AI systems have made significant strides in capturing dynamic nuances and conveying emotion, they still fall short of the expressiveness achieved by human performers.
📝 Abstract
This paper presents a comprehensive documentation of RenCon 2025, the revival of the expressive performance rendering competition which took place at ISMIR 2025 in Daejeon, Korea. The competition attracted 9 entries from international research groups, representing diverse approaches to expressive piano performance rendering. The two-phase assessment structure comprised a preliminary online evaluation and live real-time rendering at the conference. We analyze the competition format, participant demographics, system performance, and lessons learned for future iterations. The results demonstrate significant advances in expressive rendering capabilities while highlighting remaining challenges in achieving human-level musical expression.