Abstract
Considering the task of lie detection relates some nonlinear characteristics, such as psychological acoustics and auditory perception, which are difficult to be extracted and have high computational complexity. So this paper proposes a deep belief network based on the K-singular value decomposition (K-SVD) algorithm. This method combined the multi-dimensional data linear decomposition ability of sparse algorithm and the deep nonlinear network structure of deep belief network. It is aim to extract the significant time dynamic deep lie structure characteristics. Based on these deep characteristics, the lie database of Arizona University at United States was used to test. The experimental results show that, compared with the K-SVD sparse characteristics and basic acoustic characteristics, the deep characteristics proposed in this paper has better recognition rate. Furthermore, this paper provides a new exploration for psychology calculation.
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
Hu, B.: The frontier science problems and key technologies of the psychophysiological calculation. In: The 431th Academic Seminar of Xiangshan Science Conference, Beijing (2012) (in Chinese)
Shikler, T., Robinson, P.: Classification of complex information: inference of co-occurring affective states from their expressions in speech. J. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1284–1297 (2010)
Enos, F.: Detecting deception in speech, Ph.D. thesis, Columbia University (2010)
Liu, D., Shi, G., Zhou, S.: A method of signal sparse decomposition on the redundant dictionary. J. Xian Electron. Sci. Technol. Univ. (Nat. Sci. Ed.) 35, 228–232 (2008). (in Chinese)
Candès, E., Wakin, M.: An introduction to compressive sampling. J. IEEE Signal Process. Mag. 25, 21–30 (2008)
Jin, J., Gu, Y., Mei, S.: Compressed sampling technique and application. J. Electron. Inf. 32, 470–475 (2010). (in Chinese)
Candès, E., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. J IEEE Trans. Inf. Theory. 52, 489–509 (2006)
Kirchhübel, C., Howard, D.: Detecting suspicious behaviour using speech: Acoustic correlates of deceptive speech An exploratory investigation. J. Applied Ergonomics. 43, 561–569 (2012)
Zhiliang, W., Zheng, S., Wang, X.: Research status and development trend of psychological cognitive computing. J. Pattern Recogn. Artif. Intell. 24, 215–223 (2011). (in Chinese)
Gopalan, P., Wenndt, S.: Speech analysis using modulation-based features for detecting deception. In: The 15th International Conference on Digital Signal Processing. pp. 619–622 (2007)
Michal, A., Elad, M., Alfred, B.: K-SVD: an algorithm for designing over-complete dictionaries for sparse representation. J. IEEE Trans. Signal Process. 54, 4311–4322 (2006)
Anton, N.: Computational deception and noncooperation. J. IEEE Intell. Syst. 27, 60–75 (2012)
Anolli, L., Ciceri, R.: The Voice of deception: vocal strategies of naïve and able liars. J. Nonverbal Behav. 21, 259–284 (1997)
Christin, K., David, M.: Detecting suspicious behavior using speech: acoustic correlates of deceptive speech - an exploratory investigation. J. Appl. Ergon. 1–9 (2012)
Patton, M.W.: Decision support for rapid assessment for truth and deception using automated assessment technologies and kiosk-based embordied conversational agents. Ph.D. thesis, The University of Arizona (2009)
Lee, H., Largman, Y., Pham, P.: Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Neural Information Processing Systems, pp. 1–9. MIT Press, Vancouver (2009)
Dong, Y., Deng, L.: Deep learning and its applications to signal and information processing. J. IEEE Signal Process. 28, 145–154 (2011)
Ma, Y., Bao, C., Xia, B.: Speaker segmentation based on the distinctiveness deep belief network. J. Tsinghua Univ. (Nat. Sci. Ed.) 53, 804–807 (2013). (in Chinese)
Sun, Z., Xue, L., Xu, Y.: The marginal Fisher analysis feature extraction algorithm based on deep learning. J. Electron. Inf. 35, 805–811 (2013). (in Chinese)
Acknowledgment
This work was supported by the funding of the National Natural Science Foundations of China (Grant No. 61372146, No. 61373098), Innovative team foundation of Suzhou vocational university and the Innovative Plan Project for Graduate students of Jiangsu province (No. CXZZ13_0812).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhou, Y., Zhao, H., Pan, X. (2015). Lie Detection from Speech Analysis Based on K–SVD Deep Belief Network Model. In: Huang, DS., Bevilacqua, V., Premaratne, P. (eds) Intelligent Computing Theories and Methodologies. ICIC 2015. Lecture Notes in Computer Science(), vol 9225. Springer, Cham. https://doi.org/10.1007/978-3-319-22180-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-22180-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-22179-3
Online ISBN: 978-3-319-22180-9
eBook Packages: Computer ScienceComputer Science (R0)