Sleep Sound Event Detection Powered by Learnable Multi-Resolution Adaptive Line Enhancer

Chanwoo Park; Chanwoo Kim

cs.SDOct 11, 2026

Sleep Sound Event Detection Powered by Learnable Multi-Resolution Adaptive Line Enhancer

Authors: Chanwoo Park, Chanwoo Kim

Organizations: Department of Artificial Intelligence, Korea University, South Korea

Abstract

Sleep-disordered breathing, including snoring, hypopnea, and obstructive apnea, is the hallmark of obstructive sleep apnea, whose severity is quantified by the Apnea-Hypopnea Index (AHI). As conventional polysomnography is costly and clin- ically demanding, microphone-only detection has emerged as a noninvasive alternative for screening. We propose ALE- Confidence Fusion Sound Event Detection (ACF-SED), the first framework that directly injects the per-frame confidence map of an Adaptive Line Enhancer (ALE) into Transformer atten- tion biasing and feature modulation, rather than as mere pre- processing. A Multi-Resolution ALE Bank aggregates three parallel NLMS filters at distinct decorrelation delays, while a Confidence-Guided Cross-Path block couples event and noise streams via gated cross-attention. On the Audio-Polygraphy Dataset for Sleep Apnea Analysis, ACF-SED achieves state- of-the-art detection across Event-F1, Segment-F1, and PSDS, enabling end-to-end AHI estimation.

Figures & tables

Figure 1: Block diagram of STFT domain adaptive line enhancer (ALE) system.

Figure 2: Architecture of the ALE-Confidence fusion framework.

Sampling rate	4,000 Hz
Window length	25 ms
Hop length	10 ms
Learning rate	1 $e$ -4
Initial scale	0.001
Gradient clipping norm	1.0
Epoch	100

Table 1: Experimental Conditions.

Figure 3: Visualization of spectrograms for three key sleep audio events. (a) Snoring, (b) Hypopnea, (c) Obstructive sleep apnea (OSA).

Method	Event-F1	Segment-F1	PSDS
CRNN	0.6148	0.6169	0.7175
Conformer	0.5975	0.6109	0.5015
BEATs + Conformer	0.6364	0.6071	0.6949
AST	0.6710	0.6746	0.7435
Ours	0.7105	0.6930	0.7633

Table 2: Performance comparison on the APSAA evaluation set.

Subject	AHI		Severity
Subject	Pred	GT	Pred	GT
20211019A	19.05	40.79	Moderate	Severe
20211107B	31.59	39.11	Severe	Severe
20220116B	39.61	66.31	Severe	Severe
20220130C	18.40	27.82	Moderate	Moderate

Table 3: AHI estimation and OSA severity classification results on the APSAA evaluation set.

Panel of Figure 4 — Figure 4: Qualitative comparison of frame-level sleep sound event detection on a representative test recording. (a) predictions from AST [ 20 ] . (b) predictions from the proposed ACF-SED.

Figure 5: Convergence of the three learnable NLMS step sizes $\mu_{1}$ , $\mu_{2}$ , $\mu_{3}$ during training. Each $\mu_{i}$ is initialised to $0.05$ and jointly optimised with the classification objective.

$\tau$	Event-F1	Segment-F1	PSDS
1	0.7016	0.6981	0.7487
3	0.6663	0.6618	0.7308
6	0.6733	0.6625	0.7229
1,3,6	0.7105	0.6877	0.7633

Table 4: Effect of the delay parameter

\tau

in the multi-resolution ALE bank on the APSAA evaluation set. Rows with a single

\tau

value denote configurations where all three filters share the same delay;

\tau{=}\{1,3,6\}

assigns a distinct delay to each filter.

Figure 6: Comparison of spectrograms obtained from ALE processing in (top) time domain and (bottom) STFT domain, showing the original sound, enhanced output, and residual difference (from left to right).

Explore similar work

KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry
Mar 5, 2026Micky C Nnamdi, Wenqi Shi, Cheng Wan +4Medical Diagnosis Clinical Prediction
Georgia Institute of Technology Atlanta, Georgia, USA · UT Southwestern Medical Center Dallas, Texas, USA · Shriners Children’s Chicago, Illinois, USA
Speech event detector: Timestamped detection of non-verbal vocalizations and background sounds for rich speech transcription
Oct 9, 2026Ayush Kumar Bar, Promila GhoshSound Event Detection Audio Classification
Towards Open World Sound Event Detection
May 5, 2026P. H. Hai, L. T. Minh, L. H. SonContinual Learning Detection Transformer
VNU University of Engineering and Technology, Hanoi, 100000, Vietnam · Artificial Intelligence Research Center, VNU Information Technology Institute, Hanoi, 100000, Vietnam

Mar 5, 2026J/K move · Enter open · S save

KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry

Micky C Nnamdi, Wenqi Shi, Cheng Wan, J. Ben Tamo+3

Georgia Institute of Technology Atlanta, Georgia, USA · UT Southwestern Medical Center Dallas, Texas, USA · Shriners Children’s Chicago, Illinois, USA

Medical Diagnosis Clinical Prediction Concept Bottleneck Models

Open paper AskPDF arXiv

Obstructive sleep apnea (OSA) is a sleep disorder that affects nearly one billion people globally and significantly elevates cardiovascular risk. Traditional diagnosis through polysomnography is resource-intensive and limits widespread access, creating a critical need for accurate and efficient alternatives. In this paper, we introduce KindSleep, a deep learning framework that integrates clinical knowledge with single-channel patient-specific oximetry signals and clinical data for precise OSA diagnosis. KindSleep first learns to identify clinically interpretable concepts, such as desaturation indices and respiratory disturbance events, directly from raw oximetry signals. It then fuses these AI-derived concepts with multimodal clinical data to estimate the Apnea-Hypopnea Index (AHI). We evaluate KindSleep on three large, independent datasets from the National Sleep Research Resource (SHHS, CFS, MrOS; total n = 9,815). KindSleep demonstrates excellent performance in estimating AHI scores (R2 = 0.917, ICC = 0.957) and consistently outperforms existing approaches in classifying OSA severity, achieving weighted F1-scores from 0.827 to 0.941 across diverse populations. By grounding its predictions in a layer of clinically meaningful concepts, KindSleep provides a more transparent and trustworthy diagnostic tool for sleep medicine practices.

Abstract

Explore similar work

KindSleep: Knowledge-Informed Diagnosis of Obstructive Sleep Apnea from Oximetry

Speech event detector: Timestamped detection of non-verbal vocalizations and background sounds for rich speech transcription

Towards Open World Sound Event Detection