Skip to main content

Advertisement

SpringerLink
Log in

Automatic snoring sounds detection from sleep sounds based on deep learning

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

Snoring is a typical characteristic of obstructive sleep apnea hypopnea syndrome (OSAHS) and can be used for its diagnosis. The purpose of this paper is to develop an automatic snoring detection algorithm for classifying snore and non-snore sound segments, which have been segmented from a whole-night sleep sound signal using a spectral entropy method, based on convolutional neural network (CNN) descriptors extracted from audio maps. For each sound segment, the time-domain waveform, spectrum, spectrogram, Mel-spectrogram and CQT-spectrogram are calculated. Two classifiers are applied to classify sound segments into either snore or non-snore classes. The first classifier is referred to as CNNs–DNNs and combines CNNs and deep neural networks (DNNs), and the second classifier is referred to as CNNs–LSTMs–DNNs and consists of CNNs, Long and Short memory networks (LSTMs) and DNNs. The results show that the Mel-spectrogram can better reflect the differences between snore and non-snore sound segments for the five maps extracted in this study. Furthermore, the deep spectrum features extracted from CNNs–LSTMs–DNNs using Mel-spectrogram are well suited to this task. The results indicate that the method developed in this study could be used for a portable sleep monitoring device.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Strollo PJ Jr, Rogers RM (1996) Obstructive sleep apnea. N Engl J Med 334(2):99–104

    Article  Google Scholar 

  2. Lloberes P, DuránCantolla J, Martínez-García MÁ, Marín JM, Ferrer A, Corral J et al (2011) Diagnosis and treatment of sleep apnea-hypopnea syndrome. Arch Bronconeumol 47(3):143–156

    Article  Google Scholar 

  3. Qian K, Janott C, Pandit V, Zhang ZX, Heiser C, Hohenhorst W et al (2016) Classification of the excitation location of snore sounds in the upper airway by acoustic multifeature analysis. IEEE Trans Biomed Eng 64(8):1731–1741

    Article  Google Scholar 

  4. Zhao L, Huang XZ (2002) Overview of sleep snoring research. Chin Gen Pract 5(5):412–414

    Google Scholar 

  5. Abeyratne UR, Patabandi CKK, Puvanendran K (2001) Pitch-jitter analysis of snoring sounds for the diagnosis of sleep apnea. In: Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp 2072–2075

  6. Le Bon O, Staner L, Hoffmann G, Dramaix M, San Sebastian I, Murphy JR et al (2001) The first-night effect may last more than one night. J Psychiatr Res 35(3):165–172

    Article  Google Scholar 

  7. Beattie ZT, Hayes TL, Guilleminault C, Hagen CC (2013) Accurate scoring of the apnea–hypopnea index using a simple non-contact breathing sensor. J Sleep Res 22(3):356–362

    Article  Google Scholar 

  8. Emoto T, Abeyratne UR, Kawano K, Okada T, Jinnouchi O, Kawata L (2018) Detection of sleep breathing sound based on artificial neural network analysis. Biomed Signal Process Control 41:81–89

    Article  Google Scholar 

  9. Pevernagie D, Aarts RM, Meyer DE (2010) The acoustics of snoring. Sleep Med Rev 14:131–144

    Article  Google Scholar 

  10. Ip MSM, Lam B, Ng MMT, Lam WK, Tsang KWT, Lam KSL (2002) Obstructive sleep apnea is independently associated with insulin resistance. Am J Respir Crit Care Med 165(5):670–676

    Article  Google Scholar 

  11. Aldrich MS (1999) Sleep medicine. Springer, New York, USA

    Google Scholar 

  12. Perez-Padilla JR, Slawinski E, Difrancesco LM, Feige RR, Remmers JE, Whitelaw WA (1993) Characteristics of the snoring noise in patients with and without occlusive sleep apnea. Am Rev of Respir Dis 147(3):635–644

    Article  CAS  Google Scholar 

  13. Fiz JA, Abad J, Jané R, Riera M, Mananas MA, Caminal P et al (1996) Acoustic analysis of snoring sound in patients with simple snoring and obstructive sleep apnea. Eur Respir J 9(11):2365–2370

    Article  CAS  Google Scholar 

  14. Sola-Soler J, Jane R, Fiz JA, Morera J (2003) Spectral envelope analysis in snoring signals from simple snorers and patients with obstructive sleep apnea. In: Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp 2527–2530

  15. Ng AK, Koh TS, Baey E, Lee TH, Abeyratne UR, Puvanendran K (2008) Could format frequencies of snore signals be an alternative means for the diagnosis of obstructive sleep apnea. Sleep Med 9(8):894–898

    Article  Google Scholar 

  16. Duckitt WD, Tuomi SK, Niesler TR (2006) Automatic detection, segmentation and assessment of snoring from ambient acoustic data. Physiol Meas 27(10):1047–1056

    Article  CAS  Google Scholar 

  17. Cavusoglu M, Kamasak M, Erogul O, Ciloglu T, Serinagaoglu Y, Akcam T (2007) An efficient method for snore/nonsnore classification of sleep sounds. Physiol Meas 28(8):841–853

    Article  CAS  Google Scholar 

  18. Dafna E, Tarasiuk A, Zigel Y (2013) Automatic detection of whole night snoring events using non-contact microphone. PLoS ONE 8:e84139

    Article  Google Scholar 

  19. Nguyen TL, Yonggwan W (2015) Sleep snoring detection using multi-layer neural networks. Biomed Mater Eng 26:1749–1755

    Google Scholar 

  20. Mikami T, Kojima Y, Yonezawa K, Yamamoto M, Furukawa M (2013) Spectral classification of oral and nasal snoring sounds using a support vector machine. J Adv Comput Intell Intell Inform 17(4):611–621

    Article  Google Scholar 

  21. Goswami U, Black A, Krohn B, Meyers W, Iber C (2019) Smartphone-based delivery of oropharyngeal exercises for treatment of snoring: a randomized controlled trial. Sleep Breath 23(1):243–250

    Article  Google Scholar 

  22. Wang C, Peng JX, Song LJ, Zhang XW (2016) Automatic snoring sounds detection from sleep sounds via multi-features analysis. Australas Phys Eng Sci Med 40(1):1–9

    Google Scholar 

  23. Samuelsson LB, Rangarajan AA, Shimada K, Krafty RT, Buysse DJ, Strollo PJ, Kravitz HM, Zheng HY, Hall MH (2017) Support vector machines for automated snoring detection: proof-of-concept. Sleep Breath 21(1):119–133

    Article  Google Scholar 

  24. Khan T (2019) A deep learning model for snoring detection and vibration notification using a smart wearable gadget. Electronics 8(9):987

    Article  Google Scholar 

  25. Abeyratne UR, Wakwella AS, Hukins C (2005) Pitch jump probability measures for the analysis of snoring sounds in apnea. Physiol Meas 26(26):779–798

    Article  Google Scholar 

  26. Wu PP, Zhao G, Zhou M (2008) Improved spectral subtraction based on multi-window spectrum estimation. Mod Electron Technol 12:150–152

    Google Scholar 

  27. Yi H, Loizou PC (2004) Speech enhancement based on wavelet thresholding the multiaper spectrum. IEEE Trans Speech Audio Proc 12(1):59–67

    Article  Google Scholar 

  28. Scalart P, Filho JV (1996) Speech enhancement based on a priori signal to noise estimation. In: 1996 IEEE international conference on acoustics, speech, and signal processing conference proceedings. IEEE, pp 629–632

  29. New TL, Tran HD, Ng WZT, Ma B (2017) An integrated solution for snoring sound classification using Bhattacharyya distance based GMM supervectors with SVM, feature selection with random forest and spectrogram with CNN. Proc Interspeech 2017:3467–3471

    Google Scholar 

  30. Amiriparian S, Gerczuk M, Ottl S, Cummins N, Freitag M, Pugachevskiy S et al (2017) Snore sound classification using image-based deep spectrum features. Proc Interspeech 2017:3512–3516

    Article  Google Scholar 

  31. Rabiner LR, Gold B, Yuen CK (1978) Theory and application of digital signal processing. IEEE Trans Syst Man Cyber 23(2):146–146

    Article  Google Scholar 

  32. Brown JC, Puckette MS (1992) An efficient algorithm for the calculation of a constant Q transform. J Acoust Soc Am 92(5):2698–2701

    Article  Google Scholar 

  33. Schorkhuber C, Klapuri A. Constant Q transform toolbox for music processing. In: 7th Sound and Music Computing Conference, Barcelona, Spain, pp 210–217

  34. Brown JC (1991) Calculation of a constant Q spectral transform. J Acoust Soc Am 89(1):425–434

    Article  Google Scholar 

  35. Todisco M, Delgado H, Evans N (2016) A new feature for automatic speaker verification anti-spoofing: constant Q cepstral coefficients. In: Proc. ISCA Odyssey, pp 283–290

  36. Qian K, Xu ZY, Xu HJ, Wu YQ, Zhao Z (2015) Automatic detection, segmentation and classification of snore related signals from overnight audio recording. IET Signal Proc 9(1):21–29

    Article  Google Scholar 

  37. Abdel-Hamid O, Mohamed A R, Jiang H, Penn G, Yu D (2012) Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4277–4280

  38. Abdel-Hamid O, Mohamed AR, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE/ACM Trans Audio Speech Lang Process 22(10):1533–1545

    Article  Google Scholar 

  39. Sainath TN, Vinyals O, Senior A, Sak H (2015) Convolutional, long short-term memory, fully connected deep neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4580–4584

  40. Liu SY, Deng WH (2015) Very deep convolutional neural network based image classification using small training sample size. In: 2015 3rd IAPR Asian conference on pattern recognition (ACPR), pp 730–734

  41. Peng C, Zhang XY, Yu G, Luo GM, Sun J (2017) Large Kernel matters—improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4353–4361

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (81570904, 11974121).

Author information

Authors and Affiliations

  1. School of Physics and Optoelectronics, South China University of Technology, Guangzhou, 510640, China

    Yanmei Jiang & Jianxin Peng

  2. State Key Laboratory of Respiratory Disease, Department of Otolaryngology-Head and Neck Surgery, Laboratory of ENT-HNS Disease, First Affiliated Hospital, Guangzhou Medical University, Guangzhou, 510120, China

    Xiaowen Zhang

Authors
  1. Yanmei Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianxin Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaowen Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jianxin Peng or Xiaowen Zhang.

Ethics declarations

Conflict of interest

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Ethical approval

This study was approved by the Ethics Committee of Guangzhou Medical University and an informed consent was obtained from each participant.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, Y., Peng, J. & Zhang, X. Automatic snoring sounds detection from sleep sounds based on deep learning. Phys Eng Sci Med 43, 679–689 (2020). https://doi.org/10.1007/s13246-020-00876-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-020-00876-1

Keywords

Search

Navigation