Snoring Sounds Research Articles

Long Short-Term Memory Spiking Neural Networks for Classification of Snoring and Non-Snoring Sound Events

Long Short-Term Memory Spiking Neural Networks for Classification of Snoring and Non-Snoring Sound Events

Automatic detection of obstructive sleep apnea based on speech or snoring sounds: a narrative review.

Obstructive sleep apnea (OSA) is a common chronic disorder characterized by repeated breathing pauses during sleep caused by upper airway narrowing or collapse. The gold standard for OSA diagnosis is the polysomnography test, which is time consuming, expensive, and invasive. In recent years, more cost-effective approaches for OSA detection based in predictive value of speech and snoring has emerged. In this paper, we offer a comprehensive summary of current research progress on the applications of speech or snoring sounds for the automatic detection of OSA and discuss the key challenges that need to be overcome for future research into this novel approach. PubMed, IEEE Xplore, and Web of Science databases were searched with related keywords. Literature published between 1989 and 2022 examining the potential of using speech or snoring sounds for automated OSA detection was reviewed. Speech and snoring sounds contain a large amount of information about OSA, and they have been extensively studied in the automatic screening of OSA. By importing features extracted from speech and snoring sounds into artificial intelligence models, clinicians can automatically screen for OSA. Features such as formant, linear prediction cepstral coefficients, mel-frequency cepstral coefficients, and artificial intelligence algorithms including support vector machines, Gaussian mixture model, and hidden Markov models have been extensively studied for the detection of OSA. Due to the significant advantages of noninvasive, low-cost, and contactless data collection, an automatic approach based on speech or snoring sounds seems to be a promising tool for the detection of OSA.

Sleep Apnea Detection Based on Snoring Sound Analysis Using DS-MS neural network

Sleep apnea hypopnea syndrome (OSAHS) is a high-incidence disease with serious harm and potential dangers. Currently, the traditional scheme for monitoring sleep quality mainly focuses on monitoring two physiological signals: electroencephalogram (EEG) and heartbeat. However, in the sleep state, respiration is also an important physiological signal. This paper proposes a sleep apnea detection method based on snoring sound analysis using deep learning. Firstly, snoring sound signals are preprocessed and feature extraction is performed using Mel-frequency cepstral coefficients (MFCC). The extracted features are then used to train a DS-MS neural network model, and the optimal detection model is obtained through iterations. The experimental results show that the accuracy of the proposed detection model can reach 94.17%.

Identification of OSAHS patients based on ReliefF-mRMR feature selection.

Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) is a serious chronic sleep disorder. Snoring is a common and easily observable symptom of OSAHS patients. The purpose of this work is to identify OSAHS patients by analyzing the acoustic characteristics of snoring sounds throughout the entire night. Ten types of acoustic features, such as Mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC) and spectral entropy among others, were extracted from the snoring sounds. A fused feature selection algorithm based on ReliefF and Max-Relevance and Min-Redundancy (mRMR) was proposed for optimal feature set selection. Four types of machine learning models were then applied to validate the effectiveness of OSAHS patient identification. The results show that the proposed feature selection algorithm can effectively select features with high contribution, including MFCC and LPC. Based on the selected top-20 features and using a support vector machine model, the accuracies in identifying OSAHS patients under the thresholds of AHI = 5,15, and 30, were 100%, 100%, and 98.94%, respectively. This indicates that the proposed model can effectively identify OSAHS patients.

Battling with the low-resource condition for snore sound recognition: introducing a meta-learning strategy

Snoring affects 57 % of men, 40 % of women, and 27 % of children in the USA. Besides, snoring is highly correlated with obstructive sleep apnoea (OSA), which is characterised by loud and frequent snoring. OSA is also closely associated with various life-threatening diseases such as sudden cardiac arrest and is regarded as a grave medical ailment. Preliminary studies have shown that in the USA, OSA affects over 34 % of men and 14 % of women. In recent years, polysomnography has increasingly been used to diagnose OSA. However, due to its drawbacks such as being time-consuming and costly, intelligent audio analysis of snoring has emerged as an alternative method. Considering the higher demand for identifying the excitation location of snoring in clinical practice, we utilised the Munich-Passau Snore Sound Corpus (MPSSC) snoring database which classifies the snoring excitation location into four categories. Nonetheless, the problem of small samples remains in the MPSSC database due to factors such as privacy concerns and difficulties in accurate labelling. In fact, accurately labelled medical data that can be used for machine learning is often scarce, especially for rare diseases. In view of this, Model-Agnostic Meta-Learning (MAML), a small sample method based on meta-learning, is used to classify snore signals with less resources in this work. The experimental results indicate that even when using only the ESC-50 dataset (non-snoring sound signals) as the data for meta-training, we are able to achieve an unweighted average recall of 60.2 % on the test dataset after fine-tuning on just 36 instances of snoring from the development part of the MPSSC dataset. While our results only exceed the baseline by 4.4 %, they still demonstrate that even with fine-tuning on a few instances of snoring, our model can outperform the baseline. This implies that the MAML algorithm can effectively tackle the low-resource problem even with limited data resources.

Improving OSAHS Prevention Based on Multidimensional Feature Analysis of Snoring

Obstructive Sleep Apnea–Hypopnea Syndrome (OSAHS), a severe respiratory sleep disorder, presents a significant threat to human health and even endangers life. As snoring is the most noticeable symptom of OSAHS, identifying OSAHS via snoring sound analysis is vital. This study aims to analyze the time-domain and frequency-domain characteristics of snoring sounds to detect OSAHS and its severity. The snoring sounds are extracted and scrutinized from nighttime acoustic signals, with spectral energy ratio features being applied, calculated via the snore detection frequency division method. A variety of time and frequency-domain features are derived from the snoring sounds. A novel Snore Detection Cepstral Coefficient (SDCC) is proposed, based on Mel Frequency Cepstral Coefficients (MFCCs) and snore detection frequency division. Relief-F feature screening is then applied to SDCC and MFCC. Canonical Correlation Analysis (CCA) is utilized on the fusion features obtained as a result, and the results indicate the highest accuracy (97.8%) with Subspace KNN. The optimal classifier with feature combination is used for the snore model of OSASH early warnings all night, effectively recognizing and assessing OSAHS and reflecting the severity of its disease. This result, achieving high accuracy and low computational complexity, shows that the proposed method holds significant promise for developing portable sleep health detection devices.

A Classification Method Related to Respiratory Disorder Events Based on Acoustical Analysis of Snoring

Acoustical analysis of snoring provides a new approach for the diagnosis of obstructive sleep apnea hypopnea syndrome (OSAHS). A classification method is presented based on respiratory disorder events to predict the apnea-hypopnea index (AHI) of OSAHS patients. The acoustical features of snoring were extracted from a full night’s recording of 6 OSAHS patients, and regular snoring sounds and snoring sounds related to respiratory disorder events were classified using a support vector machine (SVM) method. The mean recognition rate for simple snoring sounds and snoring sounds related to respiratory disorder events is more than 91.14% by using the grid search, a genetic algorithm and particle swarm optimization methods. The predicted AHI from the present study has a high correlation with the AHI from polysomnography and the correlation coefficient is 0.976. These results demonstrate that the proposed method can classify the snoring sounds of OSAHS patients and can be used to provide guidance for diagnosis of OSAHS.

Adolescent Asthma Monitoring: A Preliminary Study of Audio and Spirometry Modalities.

Asthma patients' sleep quality is correlated with how well their asthma symptoms are controlled. In this paper, deep learning techniques are explored to improve forecasting of forced expiratory volume in one second (FEV1) by using audio data from participants and test whether auditory sleep disturbances are correlated with poorer asthma outcomes. These are applied to a representative data set of FEV1 collected from a commercially available sprirometer and audio spectrograms collected overnight using a smartphone. A model for detecting nonverbal vocalizations including coughs, sneezes, sighs, snoring, throat clearing, sniffs, and breathing sounds was trained and used to capture nightly sleep disturbances. Our preliminary analysis found significant improvement in FEV1 forecasting when using overnight nonverbal vocalization detections as an additional feature for regression using XGBoost over using only spirometry data.Clinical relevance- This preliminary study establishes up to 30% improvement of FEV1 forecasting using features generated by deep learning techniques over only spirometry-based features.

AHI estimation of OSAHS patients based on snoring classification and fusion model

Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a chronic and common sleep-breathing disease that could negatively influence lives of patients and cause serious concomitant diseases. Polysomnography(PSG) is the gold standard for diagnosing OSAHS, but it is expensive and requires overnight hospitalization. Snoring is a typical symptom of OSAHS. This study proposes an effective OSAHS screening method based on snoring sound analysis. Snores were labeled as OSAHS related snoring sounds and simple snoring sounds according to real-time PSG records. Three models were used, including acoustic features combined with XGBoost, Mel-spectrum combined with convolution neural network (CNN), and Mel-spectrum combined with residual neural network (ResNet). Further, the three models were fused by soft voting to detect these two types of snoring sounds. The subject's apnea-hypopnea index (AHI) was estimated according to these recognized snoring sounds. The accuracy and recall of the proposed fusion model achieved 83.44% and 85.27% respectively, and the predicted AHI has a Pearson correlation coefficient of 0.913 (R2 = 0.834, p < 0.001) with PSG. The results demonstrate the validity of predicting AHI based on analysis of snoring sound and show great potential for monitoring OSAHS at home.

Assessment of obstructive sleep apnea severity using audio-based snoring features

Background and ObjectiveSnoring is a prima symptom of obstructive sleep apnea (OSA). Here, we add audio-based snoring features to improve the non-obtrusive assessment of sleep apnea, by estimating the apnea-hypopnea index (AHI) and classifying OSA severity. MethodsWe propose novel features to quantify temporal changes between snores (snore rate variability) and to describe trends in snore energy, based on the assessment of snore sounds from audio signals over the full night. We then combined those features with age, body mass index (BMI) and features described in literature. An extreme gradient boosting algorithm was trained with all these features on AHI estimation. The estimated AHI was then used to classify OSA severity. ResultsAudio-based estimated AHI showed a significant Spearman's correlation with the AHI based on gold-standard polysomnography (R = 0.786, P < 0.0001). Our results outperformed a model trained with solely previously described features in our dataset (R = 0.676, P < 0.0001) and a model trained with the combination of previously described features, age, and BMI (R = 0.731, P < 0.0001). The mean absolute error of AHI estimation was 7.26 events/h. Area under the receiver operating characteristic curve outcomes were 0.90, 0.87 and 0.93 for classifying patients with varying severity separated by the canonical thresholds of 5, 15 and 30 events/h respectively. The accuracy of classifying subjects to four classes (no, mild, moderate, and severe OSA) was 59.3 %. ConclusionAdditional audio-based snore features can improve the performance of non-obtrusive AHI estimation and OSA severity classification methods.

Convolutional neural network for screening of obstructive sleep apnea using snoring sounds

Screening and assessment for obstructive sleep apnea hypopnea syndrome (OSAHS) has attracted growing attention to improve the life of patients with sleep apnea. The gold standard for diagnosing OSAHS is an overnight polysomnography (PSG) in a dedicated sleep laboratory. Yet, the PSG test is professional, expensive and unsuitable for mass screening of the population. OSAH affects about 10 % of population in the world, and there are about 80 % suffers remaining undiagnosed. The automatic and cheap OSAHS patients screening methods are urgently needed. As a major sign of undiagnosed OSAHS, snoring has been used for diagnosis of OSAHS. An automated snore detection method would allow a faster diagnosis and more patients to be analyzed. In this paper, we build a database including more than 80 thousand of snoring sound episodes from 124 subjects. These sounds are recorded by non-contact microphone in the subject’s private room, and labeled by trained sleep clinicians. And then the visibility graph method is modified as a novel framework for encoding these snoring time series into images to fully take advantage of two-dimension convolutional neural networks (CNN) in computer vision tasks. At last, a CNN model based on visibility graph method (VG) is applied to automatically extract features and recognize severity of OSAHS based on these snoring sounds. The experimental results show that our approach achieves an accuracy of 92.5 %, sensitivity of 93.9 %, and specificity of 91.2 % for OSAHS recognition. Our research provides an alternative method for rapid and massive screening and diagnosis of OSAHS.

Automatic identifying OSAHS patients and simple snorers based on Gaussian mixture models

Objective. Snoring is a typical symptom of Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS). In this study, an effective OSAHS patient detection system based on snoring sounds is presented.Approach. The Gaussian mixture model (GMM) is proposed to explore the acoustic characteristics of snoring sounds throughout the whole night to classify simple snores and OSAHS patients respectively. A series of acoustic features of snoring sounds of are selected based on the Fisher ratio and learned by GMM. Leave-one-subject-out cross validation experiment based on 30 subjects is conducted to validation the proposed model. There are 6 simple snorers (4 male and 2 female) and 24 OSAHS patients (15 male and 9 female) investigated in this work. Results indicates that snoring sounds of simple snorers and OSAHS patients have different distribution characteristics. Main results. The proposed model achieves average accuracy and precision with values of 90.0% and 95.7% using selected features with a dimension of 100 respectively. The average prediction time of the proposed model is 0.134 ± 0.005 s. Significance. The promising results demonstrate the effectiveness and low computational cost of diagnosing OSAHS patients using snoring sounds at home.

The Annoying Nature of Snoring Sounds Is Not Only about Intensity: A Pilot Study on Exposed Test Subjects.

This study aims to assess (i) which acoustic characteristics of snoring sounds are associated with the annoying nature of snoring sounds; (ii) whether listeners' heart rates correlate with their perceived annoyance; and (iii) whether perceived annoyance is different between listeners with different experiences with their bedpartners' snoring sounds. Six snoring epochs with distinct acoustic characteristics (viz., reference, high pitch, high intensity, short interval, irregular intensity, and irregular intervals) were collected from snoring patients. Twenty physicians and technicians were involved in the healthcare of snoring patients, and were divided into three groups based on personal experience with their bedpartners' snoring sounds (viz., non-snoring, snoring but not annoying, and snoring and annoying). The test subjects listened to each epoch and rated its level of annoyance. Listeners' heart rates were also recorded during the test using a finger plethysmograph. Within the limitations of this study, it was found that, compared with other snoring sounds, snoring sounds with high intensity and irregularity were associated with higher perceived annoyance. However, higher perceived annoyance of snoring sound was not reflected in heart rate-related parameters. In addition, listeners' personal experiences do not seem to affect their perceived annoyance.

Design of embedded real-time system for snoring and OSA detection based on machine learning

Obstructive sleep apnea (OSA) is a common sleep disorder. As a gold standard to detect OSA, the polysomnography (PSG) is widely used. However, the acquisition of nighttime PSG signals is very inconvenient. Compared to PSG, snoring-based OSA detection is low-cost, convenient and non-invasive. In this work, the apnea situation is studied based on the nighttime snoring signals to detect OSA. Firstly, a nighttime audio database regarding snoring sounds is built by the multi-threshold endpoint detection from original night recordings. Next, feature extraction is carried out on the segregated sound signals to obtain the characteristic information of snoring. Then, feature categories are predicted based on the machine learning models. The proposed algorithm is transplanted to the embedded device to build a real-time system which can detect snoring and OSA events. The study experiments with a variety of detection schemes and finally trains a multi-classification temporal convolutional network (TCN) to classify night audio as non-snoring, snoring or OSA-related snoring. The experiment results have achieved good performance that the detection accuracy of OSA-related snoring is up to 96.7 %. In order to further promote this method, the trained TCN model is transplanted to an embedded device to detect snoring and OSA events using as a real-time system. The experimental results fully show that the proposed detection scheme can achieve high accuracy for the detection of snoring and OSA events, which demonstrates that it can be used a new tool to conveniently help potential OSA patients understand their sleep health for home health care.

Correlation between snoring sounds and obstructive sleep apnea in adults: a meta-regression analysis

Snoring is a dominant clinical symptom in patients with obstructive sleep apnea (OSA), and analyzing snoring sounds might be a potential alternative to polysomnography (PSG) for the assessment of OSA. This study aimed to systematically examine the correlation between the snoring sounds and the apnea-hypopnea index (AHI) as the measures of OSA severity. A comprehensive literature review using the MEDLINE, Embase, Cochrane Library, Scopus, and PubMed databases identified the published studies reporting the correlations between and severity of snoring and the AHI values by meta-regression analysis. In total, 13 studies involving 3,153 adult patients were included in this study. The pooled correlation coefficient for snoring sounds and AHI values was 0.71 (95%CI: 0.49, 0.85) from the random-effects meta-analysis with the Knapp and Hartung adjustment. The I 2 and chi-square Q test demonstrated significant heterogeneity (97.6% and p<0.001). After adjusting for the effects of the other covariates, the mean value of the Fisher's r-to-z transformed correlation coefficient would have 0.80 less by the snoring rate (95%CI = -1.02, -0.57), 1.46 less by the snoring index (95%CI = -1.85, -1.07), and 0.21 less in the mean body mass index (95%CI = -0.31, -0.11), but 0.15 more in the mean age (95%CI = 0.10, 0.20). It fitted the data very well (R 2=0.9641). A high correlation between the severity of snoring and the AHI was found in the studies with PSG. As compared to the snoring rate and the snoring index, the snoring intensity, the snoring frequency, and the snoring time interval index were more sensitive measures for the severity of snoring.

Obstructive Sleep Apnea Detection Based on Sleep Sounds via Deep Learning.

This study aimed to propose a novel deep-learning method for automatic sleep apneic event detection and thus to estimate the apnea hypopnea index (AHI) and identify obstructive sleep apnea (OSA) in an event-by-event manner solely based on sleep sounds obtained by a noncontact audio recorder. We conducted a cross-sectional study of participants with habitual snoring or heavy breathing sounds during sleep to train and test a deep convolutional neural network named OSAnet for the detection of OSA based on sleep sounds. Polysomnography (PSG) was conducted, and sleep sounds were recorded simultaneously in a regular room without noise attenuation. The study was conducted in two phases. In phase one, eligible participants were enrolled and randomly allocated into training and validation groups for deep learning algorithm development. In phase two, eligible patients were enrolled in a test group for algorithm assessment. Sensitivity, specificity, accuracy, unweighted Cohen kappa coefficient (κ) and the area under the curve (AUC) were calculated using PSG as the reference standard. A total of 135 participants were randomly divided into a training group (n, 116) and a validation group (n, 19). An independent test group of 59 participants was subsequently enrolled. Our algorithm achieved a precision of 0.81 and sensitivity of 0.78 in the test group for overall sleep event detection. The algorithm exhibited robust diagnostic performance to identify severe cases with a sensitivity of 95.6% and specificity of 91.6%. Our results showed that a deep learning algorithm based on sleep sounds recorded by a noncontact voice recorder served as a feasible tool for apneic event detection and OSA identification. This technique may hold promise for OSA assessment in the community in a relatively comfortable and low-cost manner. Further studies to develop a tool based on a home-based setting are warranted.

Obstructive Sleep Apnea and Auditory Dysfunction-Does Snoring Sound Play a Role?

The objective of the study was to investigate the relationship between obstructive sleep apnea (OSA) and auditory dysfunction, and to clarify the role of snoring sounds in contributing to auditory dysfunction. A comprehensive assessment of OSA and the auditory system was performed, including overnight polysomnography, detection of the intra-ear canal snoring sound energy (SSE), pure tone average (PTA), tinnitus pitch matching, the tinnitus handicap inventory (THI), and the Epworth sleepiness scale (ESS). The patients were identified as having tinnitus if their THI score was higher than zero or their tinnitus pitches were matched to specific frequencies. The median age, body mass index, and apnea–hypopnea index score were 41 years, 26.4 kg/m2, and 29.9 events/h, respectively. Among the 50 participants, 46 (92%) had a normal PTA, and only 4 (8%) patients had mild hearing loss. There was no significant difference in PTA among OSA severities (p = 0.52). Among the 50 participants, 33 patients (66%) were identified as having tinnitus. In the tinnitus group (n = 33), the ESS score (p = 0.01) and intra-ear canal SSE of 851–1500 Hz (p = 0.04) were significantly higher than those in the non-tinnitus group (n = 17). OSA patients with a higher ESS score had a higher risk of tinnitus (odds ratio 1.22 [95% CI: 1.01–1.46]). OSA-related auditory dysfunction emerged in tinnitus rather than in hearing impairment. OSA patients with daytime sleepiness had a higher risk of tinnitus. High-frequency SSE can jeopardize cochlea and is a potential mechanism contributing to tinnitus. Detection of snoring sounds through an intra-ear canal device may be more precise in assessing acoustic trauma from snoring sounds to vulnerable auditory system and thus warrants further research.

Long-term average spectrum measures of consecutive snore sounds from different sources determined by drug-induced sleep endoscopy.

The goal of this study was to investigate the value of the long-term average spectrum in the acoustic analysis of snore sounds arising from different sources in the upper airway. Long-term average spectrum was used to analyze sequences of 10 consecutive snore sounds that had been divided into 2 groups, soft-palate type and lateral-wall type, according to the vibration site generating the snore sounds and the patterns of soft tissue collapse in the upper airway as identified by drug-induced sleep endoscopy. We calculated the first spectral peak, mean spectral energy, high-frequency energy, 0-1 kHz spectral energy, 1-5 kHz spectral energy, and 0-1 kHz/1-5 kHz difference from each group and compared the differences between them. All parameters except mean spectral energy showed significant differences between the 2 groups. The first spectral peak of less than 265.53 Hz, and the 0-1k/1-5 kHz difference of less than -11.6 dB strongly suggests soft-palate-type snore sounds. Long-term average spectrum has potential application for snore sound source identification. We recommend using first spectral peak and a 0-1 kHz/1-5 Hz difference to identify soft-palate-type snore sounds. Peng H, Xu H, Xu Z, Jia R, Yu H. Long-term average spectrum measures of consecutive snore sounds from different sources determined by drug-induced sleep endoscopy. J Clin Sleep Med. 2023;19(1):145-150.

Automatic classification of the obstruction site in obstructive sleep apnea based on snoring sounds

ObjectivesSnoring is a common symptom of obstructive sleep apnea (OSA) which is considered to be potential predictors of the obstruction site. Successful treatment of OSA depend on the determination the types of obstruction site. This study aimed to develop a machine learning-based model to detect obstruction site using snoring sound. MethodsPatients with OSA underwent drug-induced sleep endoscopy (DISE) and the snoring sounds were recorded simultaneously. We extracted acoustic features based on Mel-frequency cepstral coefficients (MFCC). A k-nearest neighbors (KNN) was used for snore classification. ResultsTotal 42 patients with OSA were enrolled. The accuracy of model was 85.55 %, F1 score was 85.04. With combined age, gender and Body Mass Index (BMI), the accuracy of model was 87.98 %, and F1 score was 87.96. The model exhibited accuracies of 83 %, 93 % and 92 %; an AUC of 85.88, 89.22 and 88.17 in detecting retropalatal, retrolingual and multilevel obstructions. ConclusionOur results suggest that combing snoring sound with age, gender and BMI, the machine learning based model can help automatically assess obstruction site. The model may have potential utility as a clinical tool to help for clinical decision-making.

Charactering Airway Collapse from PSG Trained on Snoring Sound

Charactering Airway Collapse from PSG Trained on Snoring Sound