Advertisement

A Bag of Wavelet Features for Snore Sound Classification

  • Kun QianEmail author
  • Maximilian Schmitt
  • Christoph Janott
  • Zixing Zhang
  • Clemens Heiser
  • Winfried Hohenhorst
  • Michael Herzog
  • Werner Hemmert
  • Björn Schuller
Article

Abstract

Snore sound (SnS) classification can support a targeted surgical approach to sleep related breathing disorders. Using machine listening methods, we aim to find the location of obstruction and vibration within a subject’s upper airway. Wavelet features have been demonstrated to be efficient in the recognition of SnSs in previous studies. In this work, we use a bag-of-audio-words approach to enhance the low-level wavelet features extracted from SnS data. A Naïve Bayes model was selected as the classifier based on its superiority in initial experiments. We use SnS data collected from 219 independent subjects under drug-induced sleep endoscopy performed at three medical centres. The unweighted average recall achieved by our proposed method is 69.4%, which significantly (\(p<0.005,\) one-tailed z-test) outperforms the official baseline (58.5%), and beats the winner (64.2%) of the INTERSPEECH ComParE Challenge 2017 Snoring sub-challenge. In addition, the conventionally used features like formants, mel-scale frequency cepstral coefficients, subband energy ratios, spectral frequency features, and the features extracted by the openSMILE toolkit are compared with our proposed feature set. The experimental results demonstrate the effectiveness of the proposed method in SnS classification.

Keywords

Snore sound Obstructive sleep apnea Drug-induced sleep endoscopy Wavelets Bag-of-audio-words 

Notes

Acknowledgments

This work was partially supported by the China Scholarship Council (CSC), and the European Union’s Seventh Framework under Grant Agreements No. 338164 (ERC StG iHEARu).

References

  1. 1.
    Amiriparian, S., M. Gerczuk, S. Ottl, N. Cummins, M. Freitag, S. Pugachevskiy, A. Baird, and B. Schuller. Snore sound classification using image-based deep spectrum features. In: Proceedings of INTERSPEECH, 2017, Stockholm, Sweden, pp. 3512–3516.Google Scholar
  2. 2.
    Arthur, D. and S. Vassilvitskii. K-means++: the advantages of careful seeding. In: Proceedings of ACM–SIAM SODA, 2007, New Orleans, LA, USA, pp. 1027–1035.Google Scholar
  3. 3.
    Azarbarzin, A. and Moussavi, Z. Automatic and unsupervised snore sound extraction from respiratory sound signals. IEEE Trans. Biomed. Eng. 58(5):1156–1162, 2011.CrossRefGoogle Scholar
  4. 4.
    Coifman, R. R., Y. Meyer, S. Quake, and V. Wickerhauser. Signal processing and compression with wavelet packets. In: Wavelets and Their Applications, edited by J. S. Byrnes, J. L. Byrnes, K. A. Hargreaves, and K. Berry. Dordrecht: Springer, 1994, pp. 363–379.Google Scholar
  5. 5.
    Coifman, R. R. and M. V. Wickerhauser. Entropy-based algorithms for best basis selection. IEEE Trans. Inf. Theory 38(2):713–718, 1992.CrossRefGoogle Scholar
  6. 6.
    De Bruijn, N. Uncertainty principles in Fourier analysis. In: Inequalities (Proceedings of Symposium of Wright-Patterson Air Force Base, Ohio, 1965). New York: Academic , 1967, pp. 57–71.Google Scholar
  7. 7.
    Deller Jr., J. R., J. H. L. Hansen, and J. G. Proakis. Discrete Time Processing of Speech Signals. New York: Wiley-IEEE Press, 1999.CrossRefGoogle Scholar
  8. 8.
    Demin, H., Y. Jingying, W. J. Y. Qingwen, L. Yuhua, and W. Jiangyong. Determining the site of airway obstruction in obstructive sleep apnea with airway pressure measurements during sleep. Laryngoscope 112(11):2081–2085, 2002.CrossRefGoogle Scholar
  9. 9.
    Dietterich, T. G. Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput. 10(7):1895–1923, 1998.CrossRefGoogle Scholar
  10. 10.
    Elwali, A. and Z. Moussavi. Obstructive sleep apnea screening and airway structure characterization during wakefulness using tracheal breathing sounds. Ann. Biomed. Eng., 45(3):839–850, 2017.CrossRefGoogle Scholar
  11. 11.
    Eyben, F. Real-time Speech and Music Classification by Large Audio Feature Space Extraction. Doctoral Thesis, Springer, Cham, 2015.Google Scholar
  12. 12.
    Eyben, F., F. Weninger, F. Groß, and B. Schuller. Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Proceedings of ACM MM, Barcelona, Catalunya, Spain. ACM, 2013, pp. 835–838.Google Scholar
  13. 13.
    Freitag, M., S. Amiriparian, N. Cummins, M. Gerczuk, and B. Schuller. An end-to-evolution hybrid approach for snore sound classification. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3507–3511.Google Scholar
  14. 14.
    Gosztolya, G., R. Busa-Fekete, T. Grósz, and L. Tóth. DNN-based feature extraction and classifier combination for child-directed speech, cold and snoring identification. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3522–3526.Google Scholar
  15. 15.
    Hall, M., E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten. The WEKA data mining software: an update. ACM SIGKDD Explor. Newsl. 11(1):10–18, 2009.CrossRefGoogle Scholar
  16. 16.
    Janott, C., M. Schmitt, Y. Zhang, K. Qian, V. Pandit, Z. Zhang, C. Heiser, W. Hohenhorst, M. Herzog, W. Hemmert, and B. Schuller. Snoring classified: the Munich Passau Snore Sound Corpus. Comput. Biol. Med. 94:106–118, 2018.CrossRefGoogle Scholar
  17. 17.
    Janott, C., B. Schuller, and C. Heiser. Acoustic information in snoring noise. HNO 65(2):107–116, 2017.CrossRefGoogle Scholar
  18. 18.
    Kaya, H. and K. A. Alexey. Introducing weighted kernel classifiers for handling imbalanced paralinguistic corpora: snoring, addressee and cold. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3527–3531.Google Scholar
  19. 19.
    Kezirian, E. J., W. Hohenhorst, and N. de Vries. Drug-induced sleep endoscopy: the VOTE classification. Eur. Arch. Oto-Rhino-Laryngol. 268(8):1233–1236, 2011.CrossRefGoogle Scholar
  20. 20.
    Khushaba, R. N., S. Kodagoda, S. Lal, and G. Dissanayake. Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm. IEEE Trans. Biomed. Eng. 58(1):121–131, 2011.CrossRefGoogle Scholar
  21. 21.
    LeCun, Y., Y. Bengio, and G. Hinton. Deep learning. Nature 521(7553):436–444, 2015.CrossRefGoogle Scholar
  22. 22.
    Li, K. K. Surgical therapy for adult obstructive sleep apnea. Sleep Med. Rev. 9(3):201–209, 2005.CrossRefGoogle Scholar
  23. 23.
    Lin, H.-C., M. Friedman, H.-W. Chang, and B. Gurpinar. The efficacy of multilevel surgery of the upper airway in adults with obstructive sleep apnea/hypopnea syndrome. Laryngoscope 118(5):902–908, 2008.CrossRefGoogle Scholar
  24. 24.
    Mallat, S. A Wavelet Tour of Signal Processing: The Sparse Way. Burlington: Elsevier, 2009.Google Scholar
  25. 25.
    MathWorks. Matlab Wavelet Toolbox. https://www.mathworks.com/products/wavelet.html, 2018.Google Scholar
  26. 26.
    Mlynczak, M., E. Migacz, M. Migacz, and W. Kukwa. Detecting breathing and snoring episodes using a wireless tracheal sensor-a feasibility study. IEEE J. Biomed. Health Inform. 21(6):1504–1510, 2017.CrossRefGoogle Scholar
  27. 27.
    Mokhlesi, B., S. Ham, and D. Gozal. The effect of sex and age on the comorbidity burden of OSA: an observational analysis from a large nationwide US health claims database. Eur. Respir. J. 47(4):1162–1169, 2016.CrossRefGoogle Scholar
  28. 28.
    Montazeri, A., E. Giannouli, and Z. Moussavi. Assessment of obstructive sleep apnea and its severity during wakefulness. Ann. Biomed. Eng. 40(4):916–924, 2012.CrossRefGoogle Scholar
  29. 29.
    Murty, M. N. and V. S. Devi. Pattern Recognition: An Algorithmic Approach. Dordrecht: Springer, 2011.CrossRefGoogle Scholar
  30. 30.
    Ng, A. K., T. San Koh, U. R. Abeyratne, and K. Puvanendran. Investigation of obstructive sleep apnea using nonlinear mode interactions in nonstationary snore signals. Ann. Biomed. Eng. 37(9):1796–1806, 2009a.CrossRefGoogle Scholar
  31. 31.
    Ng, A. K., T. San Koh, E. Baey, T. H. Lee, U. R. Abeyratne, and K. Puvanendran. Could formant frequencies of snore signals be an alternative means for the diagnosis of obstructive sleep apnea? Sleep Med. 9(8):894–898, 2008.CrossRefGoogle Scholar
  32. 32.
    Ng, A. K., T. San Koh, E. Baey, and K. Puvanendran. Role of upper airway dimensions in snore production: acoustical and perceptual findings. Ann. Biomed. Eng. 37(9):1807–1817, 2009b.CrossRefGoogle Scholar
  33. 33.
    Nwe, L. T., D. H. Tran, T. Z. W. Ng, and B. Ma. An integrated solution for snoring sound classification using Bhattacharyya distance based GMM supervectors with SVM, feature selection with random forest and spectrogram with CNN. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3467–3471.Google Scholar
  34. 34.
    O’Shaughnessy, D. Speech Communication: Human and Machine. New York: Addison-Wesley, 1987.Google Scholar
  35. 35.
    Pancoast, S. and M. Akbacak. Bag-of-audio-words approach for multimedia event classification. In: Proceedings of INTERSPEECH, Portland, OR, USA, 2012, pp. 2105–2108.Google Scholar
  36. 36.
    Peppard, P. E., T. Young, J. H. Barnet, M. Palta, E. W. Hagen, and K. M. Hla. Increased prevalence of sleep-disordered breathing in adults. Am. J. Epidemiol. 177(9):1006–1014, 2013.CrossRefGoogle Scholar
  37. 37.
    Pevernagie, D., R. M. Aarts, and M. De Meyer. The acoustics of snoring. Sleep Med. Rev. 14(2):131–144, 2010.CrossRefGoogle Scholar
  38. 38.
    Pishro-Nik, H. Introduction to Probability, Statistics, and Random Processes. Electrical and Computer Engineering Educational Materials, 2014. http://scholarworks.umass.edu/ece_ed_materials/1.
  39. 39.
    Qian, K., C. Janott, V. Pandit, Z. Zhang, C. Heiser, W. Hohenhorst, M. Herzog, W. Hemmert, and B. Schuller. Classification of the excitation location of snore sounds in the upper airway by acoustic multi-feature analysis. IEEE Trans. Biomed. Eng. 64(8):1731–1741, 2017.CrossRefGoogle Scholar
  40. 40.
    Qian, K., C. Janott, Z. Zhang, J. Deng, A. Baird, C. Heiser, W. Hohenhorst, M. Herzog, W. Hemmert, and B. Schuller. Teaching machines on snoring: a benchmark on computer audition for snore sound excitation localisation. Arch. Acoust. 43(3):465–475, 2018.Google Scholar
  41. 41.
    Qian, K., C. Janott, Z. Zhang, C. Heiser, and B. Schuller. Wavelet features for classification of VOTE snore sounds. In: Proceedings of ICASSP, Shanghai, China, 2016, pp. 221–225.Google Scholar
  42. 42.
    Rao, M. V. A., S. Yadav, and P. Ghosh, Kumar. A dual source-filter model of snore audio for snorer group classification. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3502–3506.Google Scholar
  43. 43.
    Rawat, S., P. F. Schulam, S. Burger, D. Ding, Y. Wang, and F. Metze. Robust audio-codebooks for large-scale event detection in consumer videos. In: Proceedings of INTERSPEECH, Lyon, France, 2013, pp. 2929–2933.Google Scholar
  44. 44.
    Reda, M., G. J. Gibson, and J. A. Wilson. Pharyngoesophageal pressure monitoring in sleep apnea syndrome. Otolaryngol. Head Neck Surg. 125(4):324–331, 2001.CrossRefGoogle Scholar
  45. 45.
    Schmitt, M., C. Janott, V. Pandit, K. Qian, C. Heiser, W. Hemmert, and B. Schuller. A bag-of-audio-words approach for snore sounds excitation localisation. In: Proceedings of ITG Speech Communication, Paderborn, Germany, 2016a, pp. 230–234.Google Scholar
  46. 46.
    Schmitt, M., F. Ringeval, and B. Schuller. At the border of acoustics and linguistics: bag-of-audio-words for the recognition of emotions in speech. In: Proceedings of INTERSPEECH, San Francisco, CA, USA, 2016b, pp. 495–499.Google Scholar
  47. 47.
    Schmitt, M. and B. W. Schuller. openXBOW-introducing the Passau open-source crossmodal bag-of-words toolkit. J. Mach. Learn. Res. 18(96):1–5, 2017.Google Scholar
  48. 48.
    Schuller, B., S. Steidl, and A. Batliner. The INTERSPEECH 2009 emotion challenge. In: Proceedings of INTERSPEECH, Brighton, UK, 2009, pp. 312–315.Google Scholar
  49. 49.
    Schuller, B., S. Steidl, A. Batliner, E. Bergelson, J. Krajewski, C. Janott, A. Amatuni, M. Casillas, A. Seidl, M. Soderstrom, S. A. Warlaumont, G. Hidalgo, S. Schnieder, C. Heiser, W. Hohenhorst, M. Herzog, M. Schmitt, K. Qian, Y. Zhang, G. Trigeorgis, P. Tzirakis, and S. Zafeiriou. The INTERSPEECH 2017 computational paralinguistics challenge: addressee, cold and snoring. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3442–3446.Google Scholar
  50. 50.
    Schuller, B., S. Steidl, A. Batliner, A. Vinciarelli, K. Scherer, F. Ringeval, M. Chetouani, F. Weninger, F. Eyben, E. Marchi, M. Mortillaro, H. Salamin, A. Polychroniou, F. Valente, and S. Kim. The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. In: Proceedings of INTERSPEECH, Lyon, France, 2013, pp. 148–152.Google Scholar
  51. 51.
    Snell, R. C. and F. Milinazzo. Formant location from LPC analysis data. IEEE Trans. Speech Audio Process., 1(2):129–134, 1993.CrossRefGoogle Scholar
  52. 52.
    Strollo Jr., P. J. and R. M. Rogers. Obstructive sleep apnea. N. Engl. J. Med. 334(2):99–104, 1996.CrossRefGoogle Scholar
  53. 53.
    Stuck, B. A. and J. T. Maurer. Airway evaluation in obstructive sleep apnea. Sleep Med. Rev. 12(6):411–436, 2008.CrossRefGoogle Scholar
  54. 54.
    Tavarez, D., X. Sarasola, A. Alonso, J. Sanchez, L. Serrano, E. Navas, and I. Hernáez. Exploring fusion methods and feature space for the classification of paralinguistic information. In: Proceedings of INTERSPEECH, Stockholm, Sweden, 2017, pp. 3517–3521.Google Scholar
  55. 55.
    Vroegop, A. V., O. M. Vanderveken, A. N. Boudewyns, J. Scholman, V. Saldien, K. Wouters, M. J. Braem, P. H. Van de Heyning, and E. Hamans. Drug-induced sleep endoscopy in sleep-disordered breathing: report on 1,249 cases. Laryngoscope 124(3):797–802, 2014.CrossRefGoogle Scholar
  56. 56.
    Yadollahi, A., A. Montazeri, A. Azarbarzin, and Z. Moussavi. Respiratory flow-sound relationship during both wakefulness and sleep and its variation in relation to sleep apnea. Ann. Biomed. Eng. 41(3):537–546, 2013.CrossRefGoogle Scholar

Copyright information

© Biomedical Engineering Society 2019

Authors and Affiliations

  1. 1.Machine Intelligence & Signal Processing Group, MMKTechnische Universität MünchenMunichGermany
  2. 2.ZD.B Chair of Embedded Intelligence for Health Care & WellbeingUniversität AugsburgAugsburgGermany
  3. 3.Munich School of BioengineeringTechnische Universität MünchenGarchingGermany
  4. 4.GLAM – Group on Language, Audio & Music, Department of ComputingImperial College LondonLondonUK
  5. 5.audEERING GmbHGilchingGermany
  6. 6.Department of Otorhinolaryngology/Head and Neck Surgery, Klinikum rechts der IsarTechnische Universität MünchenMunichGermany
  7. 7.Department of Otorhinolaryngology/Head and Neck SurgeryAlfried Krupp KrankenhausEssenGermany
  8. 8.Department of Otorhinolaryngology/Head and Neck SurgeryCarl-Thiem-Klinikum CottbusCottbusGermany

Personalised recommendations