Guardado en:
Detalles Bibliográficos
Autores principales: Feng, Tiantian, Avramidis, Kleanthis, Xu, Anfeng, Wang, Deqi, Booth, Brandon M, Narayanan, Shrikanth
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.10888
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911506381144064
author Feng, Tiantian
Avramidis, Kleanthis
Xu, Anfeng
Wang, Deqi
Booth, Brandon M
Narayanan, Shrikanth
author_facet Feng, Tiantian
Avramidis, Kleanthis
Xu, Anfeng
Wang, Deqi
Booth, Brandon M
Narayanan, Shrikanth
contents Healthcare professionals work in complex, high-stakes environments where effective communication is critical for care delivery, team coordination, and individual well-being. However, communication activity in everyday clinical settings remains challenging to measure and largely unexplored in human behavioral research. We present VoxCare, a scalable egocentric wearable audio sensing and computing system that captures natural communication behaviors of hospital professionals in real-world settings without storing raw audio. VoxCare performs real-time, on-device acoustic feature extraction and applies a speech foundation model-guided teacher-student framework to identify foreground speech activity. From these features, VoxCare derives interpretable behavioral measures of communication frequency, duration, and vocal arousal. Our analyses reveal how, when, and how often clinicians communicate across different shifts and working units, and suggest that communication activity reflects underlying workload and stress. By enabling continuous assessment of communication patterns in everyday contexts, this study provides data-driven approaches to understand the behaviors of healthcare providers and ultimately improve healthcare delivery.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10888
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VoxCare: Studying Natural Communication Behaviors of Hospital Caregivers through Wearable Sensing of Egocentric Audio
Feng, Tiantian
Avramidis, Kleanthis
Xu, Anfeng
Wang, Deqi
Booth, Brandon M
Narayanan, Shrikanth
Sound
Healthcare professionals work in complex, high-stakes environments where effective communication is critical for care delivery, team coordination, and individual well-being. However, communication activity in everyday clinical settings remains challenging to measure and largely unexplored in human behavioral research. We present VoxCare, a scalable egocentric wearable audio sensing and computing system that captures natural communication behaviors of hospital professionals in real-world settings without storing raw audio. VoxCare performs real-time, on-device acoustic feature extraction and applies a speech foundation model-guided teacher-student framework to identify foreground speech activity. From these features, VoxCare derives interpretable behavioral measures of communication frequency, duration, and vocal arousal. Our analyses reveal how, when, and how often clinicians communicate across different shifts and working units, and suggest that communication activity reflects underlying workload and stress. By enabling continuous assessment of communication patterns in everyday contexts, this study provides data-driven approaches to understand the behaviors of healthcare providers and ultimately improve healthcare delivery.
title VoxCare: Studying Natural Communication Behaviors of Hospital Caregivers through Wearable Sensing of Egocentric Audio
topic Sound
url https://arxiv.org/abs/2603.10888