RISE: Adaptive music playback for Realtime Intensity Synchronization with Exercise

2025-09-21

AI Summary

Existing workout music often fails to synchronize with users’ actual exercise rhythms (e.g., rest vs. exertion phases), leading to diminished motivation or disrupted pacing. This paper proposes a real-time synchronization method based on modular music rearrangement: it automatically identifies high-energy musical segments via audio signal analysis and dynamically reorders playback sequences and adjusts segment durations according to real-time motion intensity and predefined training protocols—thereby enabling adaptive alignment between the music’s energy profile and the user’s exertion curve. Our key contributions are (1) a decomposable and recombinable musical structure model, and (2) a dual-modal rhythm mapping mechanism bridging motion and audio domains. In a controlled 12-subject study, the system significantly improved perceived motivational accuracy (p < 0.01), and 83% of participants reported markedly enhanced exercise adherence—demonstrating the efficacy of personalized acoustic feedback in augmenting physical performance.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We propose a system to adapt a user's music to their exercise by aligning high-energy music segments with intense intervals of the workout. Listening to music during exercise can boost motivation and performance. However, the structure of the music may be different from the user's natural phases of rest and work, causing users to rest longer than needed while waiting for a motivational section, or lose motivation mid-work if the section ends too soon. To address this, our system, called RISE, automatically estimates the intense segments in music and uses component-based music rearrangement techniques to dynamically extend and shorten different segments of the user's song to fit the ongoing exercise routine. Our system takes as input the rest and work durations to guide adaptation. Currently, this is determined either via a pre-defined plan or manual input during the workout. We evaluated RISE with 12 participants and compared our system to a non-adaptive music baseline while exercising in our lab. Participants found our rearrangements keeps intensity estimation accurate, and many recalled moments when intensity alignment helped them push through their workout.

Problem

• Music structure mismatches exercise rest-work phases during workouts
• Users rest too long waiting for motivational music sections
• Motivation drops when high-energy music ends too soon

Innovation

• Aligns high-energy music with exercise intervals
• Uses component-based music rearrangement techniques
• Dynamically extends and shortens song segments