Audio Event Classification Using Deep Neural Networks

깊은 신경망을 이용한 오디오 이벤트 분류

Lim, Minkyu;Lee, Donghyun;Kim, Kwang-Ho;Kim, Ji-Hwan

  • Received : 2015.11.21
  • Accepted : 2015.12.17
  • Published : 2015.12.31


This paper proposes an audio event classification method using Deep Neural Networks (DNN). The proposed method applies Feed Forward Neural Network (FFNN) to generate event probabilities of ten audio events (dog barks, engine idling, and so on) for each frame. For each frame, mel scale filter bank features of its consecutive frames are used as the input vector of the FFNN. These event probabilities are accumulated for the events and the classification result is determined as the event with the highest accumulated probability. For the same dataset, the best accuracy of previous studies was reported as about 70% when the Support Vector Machine (SVM) was applied. The best accuracy of the proposed method achieves as 79.23% for the UrbanSound8K dataset when 80 mel scale filter bank features each from 7 consecutive frames (in total 560) were implemented as the input vector for the FFNN with two hidden layers and 2,000 neurons per hidden layer. In this configuration, the rectified linear unit was suggested as its activation function.


audio event classification;deep neural networks;mel scale filter bank


  1. K, Zvi., & T, Orith. (2013). Audio event classification using deep neural networks, in Proc. INTERSPEECH, 1482-1486.
  2. Ballan, L., et al. (2009). Deep networks for audio event classification in soccer videos, in Proc. International Conference on Multimedia and Expo, 474-477.
  3. Bengio, Y. & LeCun, Y. (2007). Scaling learning algorithms towards AI, Large-scale Kernel Machines, Vol. 34, No.5, 321-360.
  4. Barker, J., et al. (2012). The PASCAL CHiME speech separation and recognition challenge, Computer Speech & Language, Vol. 27, No. 3, 621-633.
  5. Downie, S., et al. (2010). The Music Information Retrieval Evaluation eXchange: Some observations and insights, Advances in Music Information Retrieval. Springer, 93-115.
  6. Malkin, R. G. (2007). Multimodal Technologies for Perception of Humans. Springer, 323-330.
  7. Smeaton, F. et al. (2006). Evaluation campaigns and TRECVid, in Proc. ACM International Workshop on Multimedia Information Retrieval, 321-330.
  8. Vincen, E., et al. (2012). The signal separation evaluation campaign (2007-2010): Achievements and remaining challenges, Signal Processing, Vol. 92, No. 8, 1928-1936.
  9. Larochelle, H., et al. (2007). An empirical evaluation of deep architectures on problems with many factors of variation. in Proc. International Conference on Machine learning, 473-480.
  10. Dahl, G. E., Sainath, T. N., & Hinton, G. E. (2013). Improving deep neural networks for LVCSR using rectified linear units and dropout, in Proc. International Conference on Acoustics, Speech and Signal Processing, 8609-8613.
  11. Bottou, L. (2004). Advanced Lectures on Machine Learning, Sringer, 146-168.
  12. Salamon, J., Jacoby, C., & Bello, J. P. (2014), A dataset and taxonomy for urban sound research, in Proc. ACM International Conference on Multimedia, 1041-1044.
  13. Young, S., et al. (1999). The HTK Book. Cambridge, U.K.: Entropic.
  14. Bergstra, J., et al. (2010). Theano: A CPU and GPU math expression compiler. in Proc. Python for Scientific Computing Conference, Vol. 4, p. 3.
  15. Lu, L., Jiang, H., & Zhang, H. (2001). A robust audio classification and segmentation method, in Proc. ACM International Conference on Multimedia, 203-211.
  16. Xu, M., et al. (2003). Creating audio keywords for event detection in soccer video, in Proc. IEEE International Conference on Multimedia and Expo, 281-284.
  17. Cheng, W., Chu, W., and Wu, J. (2003). Semantic context detection based on hierarchical audio models, in Proc. ACM SIGMM International Workshop on Multimedia Information Retrieval, 109-115.
  18. Elo, J. P., et al. (2009). Non-speech audio event detection, in Proc. Internationa Conference on Acoustics, Speech and Signal Processing, 1973-1976.
  19. Heittola, T., et al. (2013). Context-dependent sound event detection, EURASIP Journal on Audio, Speech, and Music Processing, 11-13.
  20. Lee, H., Pham, P., Largman, Y., & Ng, A. Y. (2009). Unsupervised feature learning for audio classification using convolutional deep belief networks. in Proc. Advances in Neural Information Processing Systems, 1096-1104.


Supported by : 정보통신기술진흥센터