Digital Audio Watermarking Method Based on Singular Spectrum Analysis with Automatic Parameter Estimation Using a Convolutional Neural Network

  • Kasorn GalajitEmail author
  • Jessada Karnjana
  • Pakinee Aimmanee
  • Masashi Unoki
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 110)


This paper proposes an audio watermarking method based on the singular-spectrum analysis (SSA) incorporating with a convolutional neural network (CNN) for parameter estimation. A watermark is embedded into an audio signal by modifying some part of its singular spectrum according to an embedding rule. Such a modified part affects both the robustness of the scheme and sound quality of watermarked signals, and it should be determined appropriately in order to balance the robustness and sound quality. In our previous work, we used a method based on a differential evolution (DE) algorithm to estimate the suitable part. However, it is a time-consuming approach. Therefore, in this work, we replace it with a CNN approach. A dataset used to train the CNN is constructed based on the DE. Experimental results show that the computational time is considerably reduced by 96,923 times. The average bit-error rate is 0.07 when there is no attack, and the sound quality of watermarked signals satisfies three objective evaluation metrics. Also, the proposed scheme could blindly extract the watermark due to the time efficiency of the CNN-based method.


Automatic parameter estimation Differential evolution Singular spectrum analysis Convolutional neural networks Audio watermarking 



This work was supported under a grant in the SIIT-JAIST-NSTDA Dual Doctoral Degree Program. It was also supported by the Grant-in-Aid for Scientific Research (B) (No.17H01761) and I-O DATA foundation.


  1. 1.
    Craver, S., Min, W., Bede, L.: What can we reasonably expect from watermarks? In: 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics, pp. 223–225. IEEE (2001)Google Scholar
  2. 2.
    Cvejic, N., Seppänen, T.: Introduction to digital audio watermarking. In: Digital Audio Watermarking Techniques and Technologies: Applications and Benchmarks, pp. 1–10. IGI Global (2008)Google Scholar
  3. 3.
    Karnjana, J., Aimmanee, P., Unoki, M., Wutiwiwatchai, C.: An audio watermarking scheme based on automatic parameterized singular-spectrum analysis using differential evolution. In: Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 543–551. Asia-Pacific (2015)Google Scholar
  4. 4.
    Karnjana, J., Unoki, M., Aimmanee, P., Wutiwiwatchai, C.: Singular-spectrum analysis for digital audio watermarking with automatic parameterization and parameter estimation. IEICE Trans. Inf. Syst. 99(8), 2109–2120 (2016)CrossRefGoogle Scholar
  5. 5.
    Bhat, V., Sengupta, I., Das, A.: An audio watermarking scheme using singular value decomposition and dither-modulation quantization. Multimed. Tools Appl. 52(2–3), 369–383 (2011)CrossRefGoogle Scholar
  6. 6.
    Hu, H.T., Hsu, L.Y.: Robust, transparent and high-capacity audio watermarking in DCT domain. Signal Process. 109, 226–235 (2015)CrossRefGoogle Scholar
  7. 7.
    Lei, B., Soon, Y., Zhou, F., Li, Z., Lei, H.: A robust audio watermarking scheme based on lifting wavelet transform and singular value decomposition. Signal Process. 92(9), 1985–2001 (2012)CrossRefGoogle Scholar
  8. 8.
    Fallahpour, M., Megías, D.: High capacity audio watermarking using the high frequency band of the wavelet domain. Multimed. Tools Appl. 52(2–3), 485–498 (2011)CrossRefGoogle Scholar
  9. 9.
    Maha, C., Maher, E., Chokri, B.A.: A blind audio watermarking scheme based on neural network and psychoacoustic model with error correcting code in wavelet domain. In: 3rd International Symposium on Communications, Control and Signal Processing, ISCCSP 2008, pp. 1138–1143 (2008)Google Scholar
  10. 10.
    Maha, C., Maher, E., Mohamed, K., Chokri, B.A.: DCT based blind audio watermarking scheme. In: Proceedings of the 2010 International Conference on Signal Processing and Multimedia Applications, pp. 139–144 (2010)Google Scholar
  11. 11.
    Lei, B., Soon, Y., Tan, E.L.: Robust SVD-based audio watermarking scheme with differential evolution optimization. IEEE Trans. Audio Speech Lang. Process. 21(11), 2368–2378 (2013)CrossRefGoogle Scholar
  12. 12.
    Storn, R., Price, K.: Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J. Glob. Optim. 11(4), 341–359 (1997)MathSciNetCrossRefGoogle Scholar
  13. 13.
    RWC database. Accessed 18 July 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Information ScienceJapan Advanced Institute of Science and TechnologyNomiJapan
  2. 2.Sirindhorn International Institute of TechnologyThammasat UniversityMuangThailand
  3. 3.NECTEC, National Science and Technology Development AgencyKhlong LuangThailand

Personalised recommendations