Juan Sebastián Gómez-Cañón | Challenges And Opportunities For Human-Centered Music Emotion Recognition
Music is intertwined with human emotion, memory, and identity, making it a powerful medium for affective experience and regulation.
Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.
Sign Up For Latest News
Music is intertwined with human emotion, memory, and identity, making it a powerful medium for affective experience and regulation.
This workshop will cover how NVIDIA RAPIDS offers a seamless experience to enable GPU-acceleration for many existing data science tasks with zero code changes. You will learn how to use GPU-accelerated tools to conduct data science faster, leading to more scalable, reliable, and cost-effective results!

This workshop will cover how NVIDIA RAPIDS offers a seamless experience to enable GPU-acceleration for many existing data science tasks with zero code changes. You will learn how to use GPU-accelerated tools to conduct data science faster, leading to more scalable, reliable, and cost-effective results!
This has motivated decades of research in music emotion recognition (MER), aiming to model emotional responses to music using computational methods. However, emotional responses to music are not fixed properties of the signal but emerge from interactions between musical structure, listener background, cultural context, and situational factors. As a result, traditional MER approaches that rely on averaged labels or universal ground truth struggle to capture the diversity and subjectivity of emotional experiences.
This talk argues for a human-centered perspective on MER that treats subjectivity not as noise but as a core signal. I discuss methodological challenges in constructing meaningful ground truth, including inter-annotator disagreement, contextual dependence, and personalization, as well as ethical concerns related to the use of emotion in a political context, and potential misuse.