Estimating Sleep-Stage Distribution from Respiratory Sounds via Deep Audio Segmentation
Sensors · 2025
DOI: 10.3390/s25206282 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Seungeon Choi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Artificial Intelligence, Hanyang University, Ansan 15588, Republic of Korea. Hauptthemen laut MEDLINE: Respiratory Sounds, Sleep Stages. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning 560 & Evaluation, Ministry of Culture, Sports and Tourism, Institute of Information & Communications Technology Planning 560 & Evaluation.
Abstract (Originalsprache)
Accurate assessment of sleep architecture is critical for diagnosing and managing sleep disorders, which significantly impact global health and well-being. While polysomnography (PSG) remains the clinical gold standard, its inherent intrusiveness, high cost, and logistical complexity limit its utility for routine or home-based monitoring. Recent advances highlight that subtle variations in respiratory dynamics, such as respiratory rate and cycle regularity, exhibit meaningful correlations with distinct sleep stages and could serve as valuable non-invasive biomarkers. In this work, we propose a framework for estimating sleep stage distribution—specifically Wake, Light (N1+N2), Deep (N3), and REM—based on respiratory audio captured over a single sleep episode. The framework comprises three principal components: (1) a segmentation module that identifies distinct respiratory cycles in respiratory sounds using a fine-tuned Transformer-based architecture; (2) a feature extraction module that derives a suite of statistical, spectral, and distributional descriptors from these segmented respiratory patterns; and (3) stage-specific regression models that predict the proportion of time spent in each sleep stage. Experiments on the public PSG-Audio dataset (287 subjects; mean 5.3 h per subject), using subject-wise cross-validation, demonstrate the efficacy of the proposed approach. The segmentation model achieved lower RMSE and MAE in predicting respiratory rate and cycle duration, outperforming classical signal-processing baselines. For sleep stage proportion prediction, the proposed method yielded favorable RMSE and MAE across all stages, with the TabPFN model consistently delivering the best results. By quantifying interpretable respiratory features and intentionally avoiding black-box end-to-end modeling, our system may support transparent, contact-free sleep monitoring using passive audio.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Applied Artificial Intelligence, Hanyang University, Ansan 15588, Republic of Korea.
- DelightRoom, Seoul 06611, Republic of Korea.
ORCID-Profile: Seungeon Choi, Joshep Shin, Yunu Kim, Jaemyung Shin, Minsam Ko
Förderung
- Institute of Information & Communications Technology Planning 560 & Evaluation
- Ministry of Culture, Sports and Tourism
- Institute of Information & Communications Technology Planning 560 & Evaluation
Zitieren
APA
Choi, S., Shin, J., Kim, Y., Shin, J., & Ko, M. (2025). Estimating Sleep-Stage Distribution from Respiratory Sounds via Deep Audio Segmentation. Sensors. https://doi.org/10.3390/s25206282
Vancouver
Choi S, Shin J, Kim Y, Shin J, Ko M. Estimating Sleep-Stage Distribution from Respiratory Sounds via Deep Audio Segmentation. Sensors. 2025. doi:10.3390/s25206282
BibTeX
@article{Choi2025,
author = {Choi, Seungeon and Shin, Joshep and Kim, Yunu and Shin, Jaemyung and Ko, Minsam},
title = {Estimating Sleep-Stage Distribution from Respiratory Sounds via Deep Audio Segmentation},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25206282}
}
EUVIMED