Democratizing Music Therapy: LLM-Based Automated EEG Analysis and Progress Tracking for Low-Cost Home Devices

TL;DR

The paper tackles the interpretability gap in home-based physiology-driven music therapy by proposing an end-to-end, LLM-assisted pipeline that converts raw $EEG$ and $HR$ data into human-readable reports and personalized music recommendations. It combines lightweight EEG/HR processing, a locally hosted LLM reasoning agent with tool augmentation, and a Retrieval-Augmented Generation-based music recommender to support post-session progress tracking. Evaluations from domain experts and a 33-participant user study show the proposed system outperforms baselines and yields emotionally coherent, user-aligned reports. This work demonstrates the practical potential of democratizing physiology-informed music therapy for home use and long-term self-regulation.

Abstract

Home-based music therapy devices require accessible and cost-effective solutions for users to understand and track their therapeutic progress. Traditional physiological signal analysis, particularly EEG interpretation, relies heavily on domain experts, creating barriers to scalability and home adoption. Meanwhile, few experts are capable of interpreting physiological signal data while also making targeted music recommendations. While large language models (LLMs) have shown promise in various domains, their application to automated physiological report generation for music therapy represents an unexplored task. We present a prototype system that leverages LLMs to bridge this gap -- transforming raw EEG and cardiovascular data into human-readable therapeutic reports and personalized music recommendations. Unlike prior work focusing on real-time physiological adaptation during listening, our approach emphasizes post-session analysis and interpretable reporting, enabling non-expert users to comprehend their psychophysiological states and track therapeutic outcomes over time. By integrating signal processing modules with LLM-based reasoning agents, the system provides a practical and low-cost solution for short-term progress monitoring in home music therapy contexts. This work demonstrates the feasibility of applying LLMs to a novel task -- democratizing access to physiology-driven music therapy through automated, interpretable reporting.

Figures (6)

• Figure 1: Pipeline of the proposed LLM-based framework.
• Figure 2: An example of a generated report for physiological signal analysis and music recommendation.
• Figure 3: A user wearing the EEG headband.
• Figure 4: The heart rate and blood oxygen saturation probe used.
• Figure 5: The hardware connections setup of the Therapy Pod.