Abstract
The lie detection from speech is difficult to be realized because it relates to many factors such as emotion, cognitive, willpower will and so on. Lying psychological state can dynamically change, and it influences the speech features obviously. However, the traditional modeling method does not fully consider the dynamic factors of speech signal, not mention to the psychological characteristics. Aiming at this problem, this paper presents a lie speech time-series modeling method based on Dynamic Sparse Bayesian Network (DSBN). This method analyzes the topology of the proposed DSBN model to achieve the probability dependence relationship of the state variables. Then the association relationship and the time series characteristic of the corresponding features can be calculated easily. The simulation experiments show that the established lying state time-series model have achieved a satisfied detection rate. The average correct detection rate has reached 76%. Therefore, the proposed time-series model is effectively, and it also provides a novel time-series modeling method for the psychological 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
Perez, G., Luis, A., Caballero, M., et al.: Multimodal emotion recognition with evolutionary computation for human-robot interaction. Expert Syst. Appl. 66, 42–61 (2016)
Billard, A.: On the mechanical, cognitive and sociable facets of human compliance and their robotic counterparts. Robot. Auton. 88, 157–164 (2017)
Marie, J.C.: Vocal fatigue induced by prolonged oral reading: analysis and detection. Comput. Speech Lang. Comput. Speech Lang. 28(2), 453–466 (2014)
Schuller, B., Steidl, S., Batliner, A., et al.: Medium-term speaker state-A review on intoxication, sleepiness and the first challenge. Comput. Speech Lang. 28(2), 346–374 (2014)
Raczynski, S.A., Vincent, E., Sagayama, S.: Dynamic bayesian networks for symbolic polyphonic pitch modeling. IEEE Trans. Audio Speech Lang. Process. 21(9), 1830–1840 (2013)
Yang, Q., Xue, D.: The gait recognition based on the double scale dynamic bayesian network and multiple information fusion. J. Electron. Inf. 34(5), 1148–1153 (2012)
Codecasa, D., Stella, F.: Classification and clustering with continuous time Bayesian network models. J. Intell. Inf. Syst. 45(2), 187–220 (2015)
Lim, C., Chang, J.: Efficient implementation techniques of an SVM-based speech/music classifier in SMV. Multimedia Tools Appl. 74(15), 5375–5400 (2015)
Han, W., Zhang, X.: The third lecture of the classical deep learning network model and the training methods. Mil. Commun. Technol. 37(1), 90–97 (2016)
Zhang, X., Chen, F., Gao, J.: Sparse bayesian and its application in time series prediction. Control Decis. Making 21(5), 585–588 (2006)
Chien, J.T., Ku, Y.C.: Bayesian recurrent neural network for language modeling. IEEE Trans. Neural Netw. Learn. Syst. 27(2), 361–374 (2016)
Zhiyong, W., Cai, L.: The audio and video double modal speaker recognition based on dynamic bayesian network. Res. Dev. Comput. 43(3), 470–475 (2006)
Acknowledgments
The authors acknowledge the National Natural Science Foundation of China (Grant: 61372146, 61373098), the Youth Natural Science Foundation of Jiangsu Province of China (Grant: BK20160361), the QingLan project of colleges and universities in Jiangsu province, the Professional Leader Advanced Research Project Foundation of Higher Vocational College of Jiangsu Province (Grant: 2017GRFX046).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zhou, Y., Zhao, H., Shang, L. (2018). Lie Speech Time-Series Modeling Based on Dynamic Sparse Bayesian Network. In: Huang, DS., Bevilacqua, V., Premaratne, P., Gupta, P. (eds) Intelligent Computing Theories and Application. ICIC 2018. Lecture Notes in Computer Science(), vol 10954. Springer, Cham. https://doi.org/10.1007/978-3-319-95930-6_40
Download citation
DOI: https://doi.org/10.1007/978-3-319-95930-6_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-95929-0
Online ISBN: 978-3-319-95930-6
eBook Packages: Computer ScienceComputer Science (R0)