AktivTalk: Digitizing the Talk Test for Voice-Based Exercise Intensity Self-Assessment and Exploring Automated Classification from Speech

2026-04-22

AI Summary

This study addresses the limitations of traditional physiological metrics in assessing exercise intensity, which are often constrained by medications or equipment and pose risks for individuals with cardiovascular disease. To overcome these challenges, the authors propose AktivTalk—the first mobile application to digitize the clinical “talk test”—leveraging structured voice interactions to combine user self-assessment with automated classification of exercise intensity. The system extracts MFCC acoustic features and employs class-balancing strategies, cross-validation, and a lightweight neural network, achieving 90% accuracy in distinguishing high versus non-high intensity exercise among 20 participants. Results demonstrate that this approach offers high usability and practicality, significantly outperforming conventional guided assessments and establishing a safe, accessible new paradigm for monitoring exercise intensity.

Technology Category

• Machine Learning: Active Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Monitoring exercise intensity is critical for safe and effective physical activity, particularly for individuals with cardiovascular disease, where overexertion can pose serious risks. Although physiological measures such as heart rate are widely used for avoiding overexertion, they can be unreliable in certain cases, such as when affected by medication or when wearables are worn too loosely. We introduce AktivTalk, a mobile prototype that digitizes the clinically validated Talk Test to support voice-based, in-the-moment self-assessment of exertion. In a within-subject study with 20 participants, we collected exertion-labeled voice samples and found that AktivTalk was rated as highly usable and preferred over conductor-guided assessment. We further explored automated exertion classification from Talk Test speech. Using MFCC-based features with class balancing and cross-validation, a lightweight neural classifier achieved up to 90% accuracy for detecting high vs.non-high exertion from Talk Test recordings. This work highlights the potential of structured voice interactions for accessible exertion assessment and motivates future passive exertion monitoring from speech.

Problem

• exercise intensity
• Talk Test
• voice-based assessment
• self-assessment
• overexertion

Innovation

• Talk Test
• voice-based exertion assessment
• automated classification
• MFCC features
• lightweight neural classifier