EarResp-ANS : Audio-Based On-Device Respiration Rate Estimation on Earphones with Adaptive Noise Suppression

TL;DR

EarResp-ANS is a novel on-device system using adaptive noise suppression to accurately estimate respiration rate from earphone audio in real-world noisy environments, with minimal energy use.

Contribution

It introduces the first fully on-device, real-time respiration rate estimation system on commercial earphones employing LMS-based adaptive noise suppression without neural networks.

Findings

Achieves a global MAE of 0.84 CPM in noisy conditions.

Reduces MAE to 0.47 CPM with outlier rejection.

Operates with less than 2% processor load on earphones.

Abstract

Respiratory rate (RR) is a key vital sign for clinical assessment and mental well-being, yet it is rarely monitored in everyday life due to the lack of unobtrusive sensing technologies. In-ear audio sensing is promising due to its high social acceptance and the amplification of physiological sounds caused by the occlusion effect; however, existing approaches often fail under real-world noise or rely on computationally expensive models. We present EarResp-ANS, the first system enabling fully on-device, real-time RR estimation on commercial earphones. The system employs LMS-based adaptive noise suppression (ANS) to attenuate ambient noise while preserving respiration-related acoustic components, without requiring neural networks or audio streaming, thereby explicitly addressing the energy and privacy constraints of wearable devices. We evaluate EarResp-ANS in a study with 18 participants under realistic acoustic conditions, including music, cafeteria noise, and white noise up to 80 dB SPL. EarResp-ANS achieves robust performance with a global MAE of 0.84 CPM , reduced to 0.47 CPM via automatic outlier rejection, while operating with less than 2% processor load directly on the earphone.