Abstract
Most existing extraction techniques in audio watermarking use conventional techniques in which some sets of special rules based on reverse embedding rules are used for watermark extraction and have many weaknesses, like very low robustness to destructive attacks. To overcome this problem, the use of machine learning-based methods has increased in recent years in this field. The disadvantage of these methods is the high reliance on a unique classifier and lack of proper efficiency when achieving high capacity, which is a major challenge in audio watermarking. The main purpose of this paper is to present a method that covers the weak points of conventional methods and simple intelligent methods and improves system performance using a synergistic combination of discrete wavelet transform (DWT) and ensemble-intelligent extraction approach by proposed combination of trained machine learning classifiers. For the embedding operation in the proposed method, the DWT and the difference in energy levels obtained through DWT coefficients are used. In the extraction section, three methods are used in parallel: (a) the trained support vector machine (SVM) classifier with RBF kernel, (b) trained SVM classifier with quadratic kernel and (c) the trained K-nearest neighbor classifier; finally, the majority function is used to vote and make a final decision to create an intelligent-based watermark detector. A training set is required to train the classifiers, whose bit sequence is generated by a proposed 5-bit linear-feedback shift register. The results of various experiments indicate that this ensemble method has achieved the appropriate imperceptibility and high capacity, along with higher robustness compared to conventional techniques and individual learning classifiers.
Similar content being viewed by others
References
Liu W, Hu AQ (2017) A subband excitation substitute based scheme for narrowband speech watermarking. Front Inf Technol Electron Eng 18(5):627–643
Latifpour H, Mosleh M, Kheyrandish M (2015) An intelligent audio watermarking based on KNN learning algorithm. Int J Speech Technol 18(4):697–706
Bruce IC, Erfani Y, Zilany MS (2018) A phenomenological model of the synapse between the inner hair cell and auditory nerve: implications of limited neurotransmitter release sites. Hear Res 360:40–54
Sun L, Xu J, Liu S, Zhang S, Li Y, Shen CA (2018) A robust image watermarking scheme using Arnold transform and BP neural network. Neural Comput Appl 30(8):2425–2440
Islam M, Roy A, Laskar RH (2020) SVM-based robust image watermarking technique in LWT domain using different sub-bands. Neural Comput Appl 32(5):1379–1403
Nejad MY, Mosleh M, Heikalabad SR (2019) An LSB-based quantum audio watermarking using MSB as arbiter. Int J Theor Phys 58(11):3828–3851
Chen K, Yan F, Iliyasu AM, Zhao J (2019) Dual quantum audio watermarking schemes based on quantum discrete cosine transform. Int J Theor Phys 58(2):502–521
Bender W, Gruhl D, Morimoto N, Lu A (1996) Techniques for data hiding. IBM Syst J 35(3.4):313–336
Mat Kiah ML, Zaidan BB, Zaidan AA, Mohammed Ahmed A, Al-Bakri SH (2011) A review of audio based steganography and digital watermarking. Int J Phys Sci 6(16):3837–3850
Peng H, Li B, Luo X, Wang J, Zhang Z (2013) A learning-based audio watermarking scheme using kernel Fisher discriminant analysis. Digit Signal Proc 23(1):382–389
Jeyhoon M, Asgari M, Ehsan L, Jalilzadeh SZ (2017) Blind audio watermarking algorithm based on DCT, linear regression and standard deviation. Multimedia Tools Appl 76(3):3343–3359
Mosleh M, Latifpour H, Kheyrandish M, Mosleh M, Hosseinpour N (2016) A robust intelligent audio watermarking scheme using support vector machine. Front Inf Technol Electron Eng 17(12):1320–1330
Mosleh M, Setayeshi S, Barekatain B, Mosleh M (2019) High-capacity, transparent and robust audio watermarking based on synergy between DCT transform and LU decomposition using genetic algorithm. Analog Integr Circ Sig Process 100(3):513–525
Pourhashemi SM, Mosleh M, Erfani Y (2019) Audio watermarking based on synergy between Lucas regular sequence and Fast Fourier Transform. Multimedia Tools Appl 78(16):22883–22908
Saadi S, Merrad A, Benziane A (2019) Novel secured scheme for blind audio/speech norm-space watermarking by Arnold algorithm. Sig Process 154:74–86
Lei B, Soon Y, Tan EL (2013) Robust SVD-based audio watermarking scheme with differential evolution optimization. IEEE Trans Audio Speech Lang Process 21(11):2368–2378
Khalil M, Adib A (2014) Audio watermarking with high embedding capacity based on multiple access techniques. Digit Signal Proc 34:116–125
Hu HT, Hsu LY (2015) Robust, transparent and high-capacity audio watermarking in DCT domain. Sig Process 109:226–235
Mohsenfar SM, Mosleh M, Barati A (2015) Audio watermarking method using QR decomposition and genetic algorithm. Multimedia Tools Appl 74(3):759–779
Chen ST, Hsu CY, Huang HN (2015) Wavelet-domain audio watermarking using optimal modification on low-frequency amplitude. IET Signal Proc 9(2):166–176
Hu HT, Hsu LY (2017) Supplementary schemes to enhance the performance of DWT-RDM-based blind audio watermarking. Circuits Syst Signal Process 36(5):1890–1911
Hu HT, Chang JR (2017) Efficient and robust frame-synchronized blind audio watermarking by featuring multilevel DWT and DCT. Clust Comput 20(1):805–816
Li R, Xu S, Yang H (2016) Spread spectrum audio watermarking based on perceptual characteristic aware extraction. IET Signal Proc 10(3):266–273
Erfani Y, Pichevar R, Rouat J (2017) Audio watermarking using spikegram and a two-dictionary approach. IEEE Trans Inf Forensics Secur 12(4):840–852
Alpaydin E (2009) Introduction to machine learning. MIT Press, Cambridge
Kantardzic M (2011) Data mining: concepts, models, methods, and algorithms. Wiley, Hoboken
Lerch A (2002) Zplane development, EAQUAL-Evaluate Audio Quality, version: 0.1.3. http://www.mp3-tech.org/programmer/misc.html. Accessed 20 Aug 2019
Lang, A. (2005). Stirmark benchmark for audio (smba): Evaluation of watermarking schemes for audio. https://sourceforge.net/projects/stirmark/. Accessed 20 Aug 2019
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Pourhashemi, S.M., Mosleh, M. & Erfani, Y. A novel audio watermarking scheme using ensemble-based watermark detector and discrete wavelet transform. Neural Comput & Applic 33, 6161–6181 (2021). https://doi.org/10.1007/s00521-020-05389-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05389-2