Improving snore detection under limited dataset through harmonic/percussive source separation and convolutional neural networks

TL;DR

This paper introduces a novel harmonic-based feature extraction method using harmonic/percussive source separation to improve snore detection with limited data, demonstrating superior performance over traditional features especially in small dataset scenarios.

Contribution

The study proposes a new harmonic spectrogram feature derived from HPSS that enhances snore detection accuracy under limited data conditions, outperforming existing features.

Findings

Harmonic spectrogram improves detection accuracy in limited data scenarios.

Proposed method outperforms traditional features in small dataset conditions.

Harmonic content aids in reliable learning of snoring sound characteristics.

Abstract

Snoring, an acoustic biomarker commonly observed in individuals with Obstructive Sleep Apnoea Syndrome (OSAS), holds significant potential for diagnosing and monitoring this recognized clinical disorder. Irrespective of snoring types, most snoring instances exhibit identifiable harmonic patterns manifested through distinctive energy distributions over time. In this work, we propose a novel method to differentiate monaural snoring from non-snoring sounds by analyzing the harmonic content of the input sound using harmonic/percussive sound source separation (HPSS). The resulting feature, based on the harmonic spectrogram from HPSS, is employed as input data for conventional neural network architectures, aiming to enhance snoring detection performance even under a limited data learning framework. To evaluate the performance of our proposal, we studied two different scenarios: 1) using a large dataset of snoring and interfering sounds, and 2) using a reduced training set composed of around 1% of the data material. In the former scenario, the proposed HPSS-based feature provides competitive results compared to other input features from the literature. However, the key advantage of the proposed method lies in the superior performance of the harmonic spectrogram derived from HPSS in a limited data learning context. In this particular scenario, using the proposed harmonic feature significantly enhances the performance of all the studied architectures in comparison to the classical input features documented in the existing literature. This finding clearly demonstrates that incorporating harmonic content enables more reliable learning of the essential time-frequency characteristics that are prevalent in most snoring sounds, even in scenarios where the amount of training data is limited.