Abstract
This paper presents the experimental results carried on the speech processing methods for paralinguistic analysis of deceptive and truthful statements. It includes a short survey of databases that contain both deceptive and truthful speech samples, as well as recently developed deception detection systems that were proposed within the framework of computational paralinguistic challenge ComParE-2016 and other scopes. Based on the analysis and comparison of different approaches for processing deceptive and truthful utterances the best methods and optimal parameters are reported as following. The highest performance in terms of Unweighted Average Recall (UAR) measure has been obtained by a Random Forest based classifier with UAR = 79.3%. High results have been shown by a single k-Nearest Neighbor classifier, as well as its combination with other classification methods such as Bagging and Classification via Regression, which demonstrated UAR = 76.3%.
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
Potapova, R., Lykova, O.: Verbal representation of lies in Russian and Anglo-American cultures. Proc. Soc. Behav. Sci. 236, 114–118 (2016)
Velichko, A.N., Budkov, V.Y., Karpov, A.A.: Analytical survey of computational paralinguistic systems for automatic recognition of deception in human speech. Informatsionno-upravliaiuschie sistemy (Information and Control Systems) 90(5), 30–41 (2017) (In Rus.)
Montacié, C., Caraty, M.-J.: Prosodic cues and answer type detection for the deception sub-challenge. In: Proceedings of INTERSPEECH-2016, San Francisco, USA, pp. 2016–2020 (2016)
Levitan, S.I., An, G., Ma, M., Levitan, R., Rosenberg A., Hirschberg J.: Combining acoustic-prosodic, lexical, and phonotactic features for automatic deception detection. In: Proceedings of INTERSPEECH-2016, San Francisco, USA, pp. 2006–2010 (2016)
Savchenko, V.V., Vasilyev, R.A.: The analysis of the emotional condition of the announcer on the voice on the basis of the phonetic lie detector. Nauchnye vedomosti Belgorodskogo gosudarstvennogo universiteta [Belgorod State University Scientific Bulletin] 21(192), 186–195 (2014) (In Rus.)
Amiriparian, S., Pohjalainen, J., Marchi, E., Pugachevskiy, S., Schuller, B.: Is deception emotional? An emotion-driven predictive approach. In: Proceedings of INTERSPEECH-2016, San Francisco, USA, pp. 201–2015 (2016)
Herms, R.: Prediction of deception and sincerity from speech using automatic phone recognition-based features. In: Proceedings of INTERSPEECH-2016, San Francisco, USA, pp. 2036–2040 (2016)
Kaya, H., Karpov, A.: Fusing acoustic feature representations for computational paralinguistics tasks. In: Proceedings of INTERSPEECH-2016, San Francisco, USA, pp. 2046–2050 (2016)
Hirschberg, J.: Detecting deceptive speech: requirements, resources and evaluation. In: LREC-2008, Marrakesh, Marokko (2008). http://www.lrecconf.org/proceedings/lrec2008/keynotes/Hirschberg.pdf. Accessed 30 Mar 2017
Kirchhübel, C., Stedmon, Alex W., Howard, D.M.: Analyzing deceptive speech. In: Harris, D. (ed.) EPCE 2013. LNCS (LNAI), vol. 8019, pp. 134–141. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39360-0_15
Pan, X., Zhao, H., Zhou, Y.: The application of fractional mel cepstral coefficient in deceptive speech detection. PeerJ (2015). https://doi.org/10.7717/peerj.1194. Accessed 30 Mar 2017
Levitan, S.I., et al.: Identifying individual differences in gender, ethnicity, and personality from dialogue for deception detection. In: NAACL-HLT-2016, San Diego, USA, pp. 40–44 (2016)
Levitan, S.I., et al.: Cross-cultural production and detection of deception from speech. In: Proceedings of ACM Workshop on Multimodal Deception Detection, Seattle, USA, pp. 1–8 (2015)
Raisov, M.E., Meshcheryakov, R.V.: Polygraph based on speech input. Nauchnaia sessiia TUSUR-2009, Tomsk 3, 344–346 (2009) (In Rus.)
Mendels, G., Levitan, S.I., Lee, K., Hirschberg, J.: Hybrid acoustic-lexical deep learning approach for deception detection. In: Proceedings of INTERSPEECH-2017, Stockholm, Sweden, pp. 1472–1476 (2017)
Schuller, B.: The INTERSPEECH 2016 computational paralinguistics challenge: deception, sincerity & native language. In: Proceedings of INTERSPEECH-2016, San Francisco, USA, pp. 2001–2005 (2016)
Pérez-Rosas, V., Abouelenien, M., Mihalcea, R., Burzo, M.: Deception detection using real-life trial data. In: Proceedings of the 2015 ACM International Conference on Multimodal Interaction, Seattle, USA, pp. 59–66 (2015)
Hirschberg, J.: Distinguishing deceptive from non-deceptive speech. In: Proceedings of INTERSPEECH-2005, Lisbon, Portugal, pp. 1833–1836 (2005)
Frank, E., Hall, M.A., Witten, I.H.: The WEKA Workbench. Online Appendix for “Data Mining: Practical Machine Learning Tools and Techniques”, 4th edn. Morgan Kaufmann (2016)
Schuller, B.: The INTERSPEECH 2013 computational paralinguistic challenge: social signals, conflict, emotion, autism. In: Proceedings of INTERSPEECH-2013, Lyon, France, pp. 148–152 (2013)
Kiefer, J., Wolfowitz, J.: Stochastic estimation of the maximum of a regression function. Ann. Mathe. Stat. 23(3), 462–466 (1952)
Platt, J.C.: Sequential minimal optimization: a fast algorithm for training support vector machines. Technical report MSR-TR-98-14, Microsoft Research, p. 21 (1998)
Frank, E., Witten, I.H.: Generating accurate rule sets without global optimization. In: International Conference on Machine Learning ICML 1998 (1998)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 119–139 (1997)
Kukreja, M., Johnson, S.A., Stafford, P.: Comparative study of classification algorithms for immunosignaturing data. BMC Bioinf. 13(139) (2012)
Pérez-Rosas, V., Mihalcea, R.: Cross-cultural deception detection. In: 52nd Annual Meeting of the Association for Computational Linguistics. Proceedings of ACL 2014, vol. 2, pp. 440–445 (2014)
Kaya, H., Karpov, A.: Efficient and effective strategies for cross-corpus acoustic emotion recognition. Neurocomputing 275, 1028–1034 (2018)
Acknowledgments
This research was supported by the Russian Foundation for Basic Research (projects No. 16-37-60085 and 18-07-01407), by the Council for Grants of the President of Russia (project No. MD-254.2017.8), and by the Government of Russia (grant No. 08-08).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Velichko, A., Budkov, V., Kagirov, I., Karpov, A. (2018). Comparative Analysis of Classification Methods for Automatic Deception Detection in Speech. In: Karpov, A., Jokisch, O., Potapova, R. (eds) Speech and Computer. SPECOM 2018. Lecture Notes in Computer Science(), vol 11096. Springer, Cham. https://doi.org/10.1007/978-3-319-99579-3_75
Download citation
DOI: https://doi.org/10.1007/978-3-319-99579-3_75
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99578-6
Online ISBN: 978-3-319-99579-3
eBook Packages: Computer ScienceComputer Science (R0)