The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지
DOI QR코드

DOI QR Code

Snoring identification method based on residual convolutional neural network

잔류 합성 곱 신경망 기반의 코골이 식별 방식

  • 신승수 (광운대학교 전자융합공학과) ;
  • 김형국 (광운대학교 전자융합공학과)
  • Received : 2019.04.23
  • Accepted : 2019.08.12
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Snoring is a typical symptom of sleep disorder and it is important to identify the occurrence of snoring because it causes sleep apnea. In this paper, we proposes a residual convolutional neural network as an efficient snoring identification algorithm. Residual convolutional neural network, which is a structure combining residual learning and convolutional neural network, effectively extracts features existing in data more than conventional neural network and improves the accuracy of snoring identification. Experimental results show that the performance of the proposed snoring algorithm is superior to that of the conventional methods.

코골이는 전형적인 수면장애 증상이며 수면 무호흡증을 유발하기 때문에 코골이의 발생을 확인하는 것이 중요하다. 이에 본 논문에서는 효율적인 코골이 식별 알고리즘으로 잔류 합성 곱 신경망을 제안한다. 잔류 학습과 합성곱 신경망을 결합한 구조인 잔류 합성 곱 신경망은 기존의 신경망보다 데이터에 존재하는 특징을 효과적으로 추출하여 코골이 식별 정확도를 향상한다. 실험 결과는 제안한 코골이 식별 알고리즘의 성능이 기존 방식보다 더 우수하다는 것을 보여준다.

Keywords

References

  1. S. Sharma and A. Culebras, "Sleep apnea and stroke," Stroke Vasc Neurol, 1, 185-191 (2016). https://doi.org/10.1136/svn-2016-000038
  2. W. K. Jang, S. P. Cho, and K. J. Lee, "A study for snoring detection based artificial neural network" (in Korean), Trans. KIEE, 51, 327-333 (2002).
  3. B. M. Kim and C. B. Moon, "Snoring sound classification using efficient spectral features and SVM for smart pillow" (in Korean), JKSIIS., 23, 11-18 (2018).
  4. E. Dafna, A. Tarasiuk, and Y. Zigel, "Automatic detection of snoring events using Gaussian mixture models," MAVEBA, 17-22 (2011).
  5. S. Amiriparian, M. Gerczuk, S. Ottl, N. Cummins, M. Freitag, S. Pugachevskiy, A. Baird, and B. Schuller, "Snore sound classification using image-based deep spectrum features," Proc. Interspeech 2017, 3512-3516 (2017).
  6. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, "Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising," IEEE Trans. Image Process, 26, 3142-3155 (2017). https://doi.org/10.1109/TIP.2017.2662206
  7. I. S. Jang, C. H. Ahn, and Y. S. Jang, "Non-dialog section detection for the descriptive video service contents authoring" (in Korean), J. Broadcast Engineering, 19, 296-306 (2014). https://doi.org/10.5909/JBE.2014.19.3.296
  8. S. H. Ryu and H. G. Kim, "Audio mixer algorithm for enhancing speech quality of multi-party audio telephony" (in Korean), J. Acoust. Soc. Kr. 32, 541-547 (2013). https://doi.org/10.7776/ASK.2013.32.6.541
  9. B. Yue, J. Fu, and J. Liang, "Residual recurrent neural networks for learning sequential representations," Information, 9, 1-14 (2018). https://doi.org/10.3390/info9010001
  10. S. Gupta, J. Jaafar, W. F. Wan Ahmad, and A. Bansal, "Feature extraction using mfcc," SIPIJ. 4, 101-108