DOI QR코드

DOI QR Code

Scream Sound Detection Based on Universal Background Model Under Various Sound Environments

다양한 소리 환경에서 UBM 기반의 비명 소리 검출

  • 정용주 (계명대학교 전자공학과)
  • Received : 2017.04.09
  • Accepted : 2017.06.16
  • Published : 2017.06.30

Abstract

GMM has been one of the most popular methods for scream sound detection. In the conventional GMM, the whole training data is divided into scream sound and non-scream sound, and the GMM is trained for each of them in the training process. Motivated by the idea that the process of scream sound detection is very similar to that of speaker recognition, the UBM which has been used quite successfully in speaker recognition, is proposed for use in scream sound detection in this study. We could find that UBM shows better performance than the traditional GMM from the experimental results.

GMM(: Gaussian Mixture Model)은 비명 소리를 검출하기 위해서 가장 많이 사용되는 기법의 하나이다. 기존의 GMM 방식에서는 전체 훈련데이터를 비명소리와 비-비명 소리로 나누고, 훈련과정을 통하여 각각의 GMM 모델을 생성하게 된다. 그러나 본 연구에서는 비명 소리 검출 과정이 화자인식과 매우 유사하다는 점에 착안하여 화자인식에서 매우 효과적으로 사용된 UBM(: Universal Background Model) 방식을 비명소리 검출에 적용할 것을 제안하였다. 제안된 UBM 방식을 통한 검출 실험 결과 기존의 GMM 방식에 비하여 더 나은 검출 성능을 보임을 인식 실험을 통하여 확인 할 수 있었다.

Keywords

References

  1. W. Kim, Y. Kim and G. Lee, "Sound recognition and tracking system design using robust sound extraction section", J. of the Korea Institute of Electronic Communication Sciences, vol. 11, no. 8, 2016, pp. 759-766. https://doi.org/10.13067/JKIECS.2016.11.8.759
  2. J. H. Seo, H. Lee and S. Lee, "A Design of a scream detecting engine for surveillance systems", The Korean Institute of Electrical Engineers, vol. 63, no. 11, 2014, pp. 1559-1563, Nov. 2014. https://doi.org/10.5370/KIEE.2014.63.11.1559
  3. S. Ntalampiras, I. Potamitis and N. Fakotakis, "On acoustic surveillance of hazardous situations", In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, Tapei, Taiwan, April 2009, pp. 165-168.
  4. J. Park, J. Lim, J. Yang, J. Kyung and M. Hahn, "False Positive Movie Clip Decision in Black-box Using Car Door-Closing Sound Classification", The Institute of Electronics and Information Engineers, vol. 37, no. 1, June. 2014, pp. 761-763.
  5. J. Pohjalainen, P. Alku and T. Kinnunen, "Shout detection in noise", in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, May 2011, pp. 4968-4971.
  6. L. Gerosa, G. Valenzise, M. Tagliasacchi, F. Antonacci and A. Sarti, "Scream and Gunshot Detection in Noisy Environments", in Proc. European Signal Processing Conference, Poznan, Poland, Sept. 2007, pp. 1216-1220.
  7. K. Imoto and N. Ono, "Acoustic scene analysis from acoustic event sequence with intermittent missing event" in Proc. IEEE International Conference on Acoustics Speech and Signal Processing., South Brisbane, Australia, 2015, pp.156-159.
  8. S. Chung and Y. Chung, "A comparision between methods for scream detection based on SVM and GMM", J. of Korean Institute of Information Technology, vol. 15, no. 3, Mar. 2017, pp. 65-72.
  9. D. Reynolds, T. Quatieri and R. Dunn, "Speaker verification uisng adapted Gaussian mixture model", Digital Signal Processing, vol. 10, no.1, 2000, pp.19-41. https://doi.org/10.1006/dspr.1999.0361
  10. W. Huang, T. K. Chiew, H. Li, T. S. Kok and J. Biswas, "Scream detection for home applications", in Proc. of IEEE Conference on Industrial Electronics and Applications, June 2010, pp. 2115-2120.
  11. ETSI draft standard doc., Speech Processing, Transmission and Quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithm. ETSI Standard ES 202 050, 2002.
  12. J. Lee, "A study on face recognition system using LDA and SVM", J. of the Korea Institute of Electronic Communication Sciences, vol. 10, no. 11, 2015, pp. 1307-1314. https://doi.org/10.13067/JKIECS.2015.10.11.1307