Abstract
With the easy acquisition of digital recordings, the field of audio forensics has become increasingly prominent. Detection of audio compression history is an important issue in the field of audio forensics. In this paper, a detection framework is proposed to detect whether a given audio waveform is an original waveform or a decompressed one. We extract the spectrum features from the frequency domain and then adopt a stacked autoencoder to effectively detect the frame-level audio fragments to distinguish between the original audio frames and the decompressed audio frames. Then, a majority voting algorithm is applied to make the final decision for an audio clip. Our analysis focuses on multi-time compressed audio, including single compression, double compression, triple compression and even four-time compression in three kinds of compression formats. The experimental results show that the proposed framework can effectively detect multi-time compressed audio. Furthermore, the proposed framework can also estimate the compression bitrate.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barni, M., Chen, Z., Tondi, B.: Adversary-aware, data-driven detection of double JPEG compression: how to make counter-forensics harder. In: IEEE International Workshop on Information Forensics and Security (2016). https://doi.org/10.1109/wifs.2016.7823902
Pevný, T., Fridrich, J.: Detection of double-compression in JPEG images for applications in steganography. IEEE Trans. Inf. Forensics Secur. 3(2), 247–258 (2008)
Galvan, F., Puglisi, G., Bruna, A., Battiato, S.: First quantization matrix estimation from double compressed JPEG images. IEEE Trans. Inf. Forensics Secur. 9(8), 1299–1310 (2014)
Yang, R., Shi, Y., Huang, J.: Defeating fakequality MP3. In: Proceedings of ACM Workshop Multimedia Security, Princeton, NJ, USA, pp. 117C-124 (2009)
Yang, R., Shi, Y., Huang, J.: Detecting double compression of audio signal. In: Procedings of SPIE Electronic Imaging. International Society for Optics and Photonics, 75410 K-75410 K-10 (2010)
Qiao, M., Sung, A., Liu, Q.: Revealing real quality of double compressed MP3 audio. In: Proceedings of the International Conference on Multimedia, pp. 1011–1014 (2010)
Liu, Q., Sung, A., Qiao, M.: Detection of double MP3 compression. Cognit. Comput. 2(4), 291–296 (2010)
Ma, P., Wang, R., Yan, D., Jin, C.: A Huffman table index based approach to detect double MP3 compression. In: Shi, Y.Q., Kim, H.J., Pérez-González, F. (eds.) IWDW 2013. LNCS, vol. 8389, pp. 258–271. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-43886-2_19
Bießmann, P., et al.: Estimating MP3PRO encoder parameters from decoded audio. In: Proceedings of GI-Jahrestagung, 2841C–2852 (2013)
Yan, D., Wang, R., Zhou, J., Jin, C., Yang, Z.: Compression history detection for MP3 audio. KSII Trans. Internet Inf. Syst. 12(2), 662–675 (2018)
Jenner, F., Kwasinsk, A.: Highly accurate non-intrusive speech forensics for codec identifications from observed decoded signals. In: Proceedings of International Conference Acoustic, Speech and Signal Process, Kyoto, Japan, pp. 1737–1740 (2012)
Hiçsönmez, S., Sencar, H., Avcibas, I.: Audio codec identification through payload sampling. In: Proceedings of Workshop Information Forensics Security (2011). https://doi.org/10.1109/wifs.2011.6123128
Hiçsönmez, S., Uzun, E., Sencar, H.: Methods for identifying traces of compression in audio. In: Proceedings of 1st International Conference Communication, Signal Processing and Application, Sharjah, United Arab Emirates (2013). https://doi.org/10.1109/iccspa.2013.6487284
Hennequin, R., Royo-Letelier, J., Moussallam, M.: Codec independent lossy audio compression detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 726–730 (2017)
Luo, D., Luo, W., Yang, R., Huang, J.: Identifying compression history of wave audio and its applications. ACM Trans. Multimed. Comput. Commun. Appl. (TOMCCAP), 10(3), 30 (2014)
Huang, Q., Wang, R., Yan, D., Zhang, J.: AAC double compression audio detection algorithm based on the difference of scale factor. Information 9(7), 161 (2018)
Shen, Y., Jia, J., Cai, L.: Detecting double compressed AMR-format audio recordings. In Proceedings of 10th Phonetics Conference of China (2012)
Luo, D., Yang, R., Huang, J.: Detecting double compressed AMR audio using deep learning. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2688–2692 (2014)
Luo, D., Yang, R., Li, B., Huang, J.: Detection of double compressed AMR audio using stacked autoencoder. IEEE Trans. Inf. Forensics Secur. 12(2), 432–444 (2017)
Gärtner, D., Dittmar, C., Aichroth, P., Cuccovillo, L., Mann, S., Schuller, G.: Efficient cross-codec framing grid analysis for audio tampering detection. In: Proceedings of Audio Engineering Society Convention, p. 136 (2014)
Gärtner, D., Cuccovillo, L., Mann, S., Aichroth, P.: A multi-codec audio dataset for codec analysis and tampering detection. In: Proceedings of 54th Audio Engineering Society Conference on Audio Forensics (2014)
Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Reynolds, D., Quatieri, T., Dunn, R.: Speaker verification using adapted gaussian mixture models. Digit. Signal Process. 10(1–3), 19–41 (2000)
Kingma, D.: Max welling: auto-encoding variational Bayes. arXiv:1312.6114 [stat.ML] (2013)
Kan, X., et al.: Snow cover mapping for mountainous areas by fusion of MODIS L1B and geographic data based on stacked denoising auto-encoders. Comput. Mater. Continua 57(1), 49–68 (2018)
Zhao, X., Jiaxin, W., Zhang, Y., Shi, Y., Wang, L.: Fault diagnosis of motor in frequency domain signal by stacked de-noising auto-encoder. Comput. Mater. Continua 57(2), 223–242 (2018)
Acknowledgments
The work presented in this paper was supported in part by the NSFC (61602318, 61672551, 61631016, 61972090), the Guangzhou Science and Technology Plan Project under Grant 201707010167, the Science and Technology planning project of Guangdong Province (2014A010103039, 2015A010103022).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Luo, D., Cheng, W., Yuan, H., Luo, W., Liu, Z. (2020). Compression Detection of Audio Waveforms Based on Stacked Autoencoders. In: Sun, X., Wang, J., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2020. Lecture Notes in Computer Science(), vol 12240. Springer, Cham. https://doi.org/10.1007/978-3-030-57881-7_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-57881-7_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-57880-0
Online ISBN: 978-3-030-57881-7
eBook Packages: Computer ScienceComputer Science (R0)