Journal of Networks, Vol 7, No 6 (2012), 908-917, Jun 2012
doi:10.4304/jnw.7.6.908-917

Identifying Microphone from Noisy Recordings by Using Representative Instance One Class-Classification Approach

Huy Quan Vu, Shaowu Liu, Xinghua Yang, Zhi Li, Yongli Ren

Abstract


Rapid growth of technical developments has created huge challenges for microphone forensics - a sub-category of audio forensic science, because of the availability of numerous digital recording devices and massive amount of recording data. Demand for fast and efficient methods to assure integrity and authenticity of information is becoming more and more important in criminal investigation nowadays. Machine learning has emerged as an important technique to support audio analysis processes of microphone forensic practitioners. However, its application to real life situations using supervised learning is still facing great challenges due to expensiveness in collecting data and updating system. In this paper, we introduce a new machine learning approach which is called One-class Classification (OCC) to be applied to microphone forensics; we demonstrate its capability on a corpus of audio samples collected from several microphones. In addition, we propose a representative instance classification framework (RICF) that can effectively improve performance of OCC algorithms for recording signal with noise. Experiment results and analysis indicate that OCC has the potential to benefit microphone forensic practitioners in developing new tools and techniques for effective and efficient analysis.


Keywords


Machine Learning, Data Mining, Audio Forensics, Microphone Forensics, One-Class Classification

References


 

[1] C. Kraetzer, A. Oermann, J. Dittmann, and A. Lang, “Digital Audio Forensics : A First Practical Evaluation on Microphone and Environment Classification,” in Proceedings of the 9th workshop on Multimedia and security, Dallas, Texas, September 2007, pp. 63–74.

[2] C. Kraetzer, M. Schott, and J. Dittmann, “Unweighted fusion in microphone forensics using a decision tree and linear logistic regression models,” in Proceedings of the 11th workshop on Multimedia and security. Princeton, New Jersey, USA: ACM Press, September 2009, pp. 49–56.

[3] R. Buchholz, C. Kraetzer, and J. Dittmann, “Microphone Classification Using Fourier Coefficients,” Lecture Notes in Computer Science, vol. 5806, pp. 235–246, 2009.
http://dx.doi.org/10.1007/978-3-642-04431-1_17

[4] D. Garcia Romero and C. Y. Espy Wilson, “Automatic acquisition device identification from speech recordings,” in Proceeding of IEEE International Conference on Acoustics Speech and Signal Processing, Dallas, Texas, US, March 2010, pp. 1806–1809.
http://dx.doi.org/10.1109/ICASSP.2010.5495407

[5] C. Kraetzer, K. Qian, M. Schott, and J. Dittmann, “A context model for microphone forensics and its application in evaluations,” Media Watermarking, Security, and Forensics III, vol. 7880, p. In Press, 2011.

[6] A. Rabaoui, H. Kadri, Z. Lachiri, and N. Ellouze, “One-Class SVMs Challenges in Audio Detection and Classification Applications,” EURASIP Journal on Advances in Signal Processing, vol. 2008, pp. 1–14, 2008.
http://dx.doi.org/10.1155/2008/834973

[7] A. Rabaoui, M. Davy, S. Rossignol, and Z. Lachiri, “Improved one-class svm classifier for sounds classification,” in Proceeding of IEEE Conference on Advanced Video and Signal Based Surveillance, London, United Kingdom, September 2007, pp. 117–122.

[8] G. FengJuan, S. ShuQian, and W. XiaoHui, “Using One-Class SVMs and MP for Audio Recognition of Action Scenes,” in Proceeding of 2nd International Workshop on Education Technology and Computer Science, Wuhan, China, March 2010, pp. 401–404.

[9] A. Brew, M. Grimaldi, and P. Cunningham, “An evaluation of one-class classification techniques for speaker verification,” Artificial Intelligence Review, vol. 27(4), pp. 295–307, 2008.
http://dx.doi.org/10.1007/s10462-008-9071-8

[10] M. O. AlQahtani, G. Muhammad, and Y. A. Alotaibi, “Environment Sound Recognition using Zero Crossing Features andl MPEG-7,” in Proceeding of Fifth International Conference on Digital Information Management, Thunder Bay, Ontario, Canada, July 2010, pp. 502–506.

[11] N. Sen, T. K. Basu, and H. A. Patil, “Significant Improvement in the Closed Set Text- Independent Speaker Identification Using Features Extracted from Nyquist Filter Bank,” in Proceeding of 5th International Conference on Industrial and Information Systems, India, Jul 2010, pp. 303–308.
http://dx.doi.org/10.1109/ICIINFS.2010.5578690

[12] I. L. Freire and J. A. Apolinario Jr., “Gunshot detection in noisy environments,” in Proceeding of the 7th International Telecommunications Symposium, Manaus, Brazil, September 2010.

[13] P. Dhanalakshmi, S. Palanivel, and V. Ramalingam, “Classification of audio signals using AANN and GMM,” Applied Soft Computing, vol. 11, no. 1, pp. 716–723, Jan. 2011.
http://dx.doi.org/10.1016/j.asoc.2009.12.033

[14] M. O. Alqahtani and A. S. Al mazyad, “Environment Sound Recognition for Digital Audio Forensics Using Linear Predictive Coding Features,” in Proceeding of International Conference on Digital Information Processing and Communications, Ostrava, Czech Republic, July 2011, pp. 301–309.

[15] J. Rong, G. Li, and Y.-P. P. Chen, “Acoustic feature selection for automatic emotion recognition from speech,” Information Processing and Management, vol. 45(3), pp.315–328, 2008.
http://dx.doi.org/10.1016/j.ipm.2008.09.003

[16] J. Ye, “Speech recognition using time domain features from phase space reconstructions,” Ph.D. dissertation, Marquette University, Milwaukee, Wisconsin, May 2004.

[17] W. Florian, “An introduction to mds,” Aalborg University, Denmark, Tech. Rep., 2003.

[18] D. Tax, “Data description toolbox dd tools 1.7.5,” Delft University of Technology, Delft, The Netherlands, Tech. Rep., May 2010.

[19] D. M. Tax and R. P. Duin, “Support vector domain description,” Pattern Recognition Letters, vol. 20, pp. 1191–1199, 1999.
http://dx.doi.org/10.1016/S0167-8655(99)00087-2

[20] A. Rabaoui, M. Davy, S. Rossignol, and N. Ellouze, “Using one-class svms and wavelets for audio surveillance,” IEEE Transactions on Information Forensics and Security, vol. 3(4), pp. 763–775, 2008.
http://dx.doi.org/10.1109/TIFS.2008.2008216

[21] T. Hastie, R. Tibshirani, and J. Friedman, Eds., The Elements of Statistical Learning. New York: Springer, 2001, ch. 6.

[22] G. R. Terrell and D. W. Scott, “Variable kernel density estimation,” The Annals of Statistics, vol. 20(3), The Annals of Statistics, 1992.


Full Text: PDF


Journal of Networks (JNW, ISSN 1796-2056)

Copyright @ 2006-2013 by ACADEMY PUBLISHER – All rights reserved.