Industry Expert Talk: From ANC to Blood Pressure: How Earbuds Are Becoming Multimodal Health Sensors
This presentation explores the transformation of true wireless earbuds from basic audio playback devices into multimodal, health-monitoring wearable platforms. Driven by the unique anatomical advantages of the ear—including stable skin contact, rich local vasculature, and reduced motion interference from the musculoskeletal system—in-ear sensing is positioned to mirror the evolution of smartwatches toward continuous biometric tracking. The primary objective is to demonstrate how integrated signal processing and multi-sensor co-design enable earables to perform low-power, real-time vital sign monitoring and cuffless blood pressure measurement directly at the edge without reliance on cloud processing.
Key focus areas include the deployment of optical photoplethysmography (PPG) to track heart rate, heart-rate variability, oxygen saturation, and respiration rate. Experimental evaluation demonstrates that in-the-canal (ITC) placement significantly improves signal fidelity and ambient-light shielding compared to behind-the-ear or in-the-ear configurations, though motion artifacts during activities like running remain a major source of error (up to 30%). To address cuffless blood pressure (BP) estimation, the talk introduces a single-earbud technique combining in-ear PPG with an acoustic microphone capturing attenuated heart sounds (
S
1
S
1
?
/
S
2
S
2
?
) via the occlusion effect. By extracting timing metrics such as vascular transit time (
S
1
?
PPG peak
S
1
?
?PPG peak) and ejection time (
S
1
?
S
2
S
1
?
?S
2
?
), a pilot evaluation on 10 healthy subjects achieved mean absolute errors of
2.50
±
2.20
mmHg
2.50±2.20 mmHg for systolic BP and
2.42
±
2.62
mmHg
2.42±2.62 mmHg for diastolic BP under induced physiological changes.
Ultimately, turning earbuds into reliable, medical-grade health platforms requires solving critical signal processing challenges, including suppressing motion artifacts, maintaining performance during active noise cancellation or music playback, and balancing personalization with cross-subject generalization. By tightly integrating low-compute time-domain pipelines, optimized ear-tip mechanics, and on-device multi-sensor fusion, earables present a compelling frontier for privacy-preserving, continuous health monitoring in everyday life.
