The Most Important Features of Lie Detection Using Voice Stress

Authors

  • Fadi K. Al-Dhaher College of Engineering, Al-Iraqia University, Baghdad, Iraq
  • Duraid Y. Mohammed College of Engineering, Al-Iraqia University, Baghdad, Iraq
  • Mohammed Khalaf General Directorate of Education Anbar, Ramadi 31001, Iraq / Computer Science Department, Al-Maarif University College, Ramadi 31001, Iraq

DOI:

https://doi.org/10.58564/IJSER.3.1.2024.149

Keywords:

Voice stress, Lie speech, Random Forest (RF), Deception detection, Machine learning

Abstract

 

 This study proposes a lie detection module that leverages audio features in both the time and frequency domains to scrutinize key features and speech patterns for more precise dishonesty detection. The research focuses on addressing the limitations of traditional methods and suggests practical alternatives, aiming to contribute to the improvement of existing understanding and system architectures in the field of deception detection. where Detecting deception is critical in various fields, such as law enforcement, national security, and personal relationships. While traditional methods like polygraph exams are criticized for their reliability, emerging real-time technologies like voice stress analysis and speech processing techniques present alternatives. This research aims to enhance lie detection systems by exploring the potential of audio features, offering a more nuanced approach to identifying dishonesty, and overcoming the limitations of current methods. The study introduces a lie detection algorithm utilizing a real-world dataset collected with a handheld microphone, replicating authentic situations. Feature selection employs the random forest technique, focusing on the most significant features for training and testing. The algorithm achieved a 79% accuracy rate through rigorous examination, with Mel-frequency cepstral coefficients (MFCC) identified as the crucial feature for lie detection. This underscores the method's potential effectiveness in real-time fraud detection. However, further research is necessary to confirm its consistency across various datasets, situations, and demographic groups.

References

A. Xue, H. Rohde, and A. Finkelstein, “An Acoustic Automated Lie Detector,” 2019.

I. J. Mohammed and L. E. George, “Lie Detection and Truth Identification form EEG signals by using Frequency and Time Features,” J Algebr Stat, vol. 13, no. 3, pp. 4102–4121, 2022, [Online]. Available: https://publishoa.comhttps://publishoa.com

S. V. Fernandes and M. S. Ullah, “Use of Machine Learning for Deception Detection from Spectral and Cepstral Features of Speech Signals,” IEEE Access, vol. 9, pp. 78925–78935, 2021, doi: 10.1109/ACCESS.2021.3084200.

F. M. Marcolla, R. de Santiago, and R. L. S. Dazzi, “Novel lie speech classification by using voice stress,” in ICAART 2020 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence, SciTePress, 2020, pp. 742–749. doi: 10.5220/0009038707420749.

E. P. Fathima Bareeda, B. S. Shajee Mohan, and K. V. Ahammed Muneer, “Lie Detection using Speech Processing Techniques,” in Journal of Physics: Conference Series, IOP Publishing Ltd, May 2021. doi: 10.1088/1742-6596/1921/1/012028.

H. C. Chou, Y. W. Liu, and C. C. Lee, “Automatic deception detection using multiple speech and language communicative descriptors in dialogs,” APSIPA Trans Signal Inf Process, 2021, doi: 10.1017/ATSIP.2021.6.

S. Mihalache and D. Burileanu, “Using Voice Activity Detection and Deep Neural Networks with Hybrid Speech Feature Extraction for Deceptive Speech Detection,” Sensors, vol. 22, no. 3, Feb. 2022, doi: 10.3390/s22031228.

F. M. Talaat, “Enhanced Deep Neural Network for Lie Detection by using Voice Stress,” 2021. Accessed: Sep. 20, 2022. [Online]. Available: https://www.researchgate.net/publication/366606445_Deep_Neural_Network_for_Lie_Detection_Based_on_Voice_Stress

X. S. H. F. B. W. and T. Y. W. Wang, “‘Machine Learning based Deceptive Speech Detection,’ 2023 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Erode, India, 2023, pp. 1-6,”, doi: 10.1109/ICSCDS56580.2023.10104721.

H. Fu, H. Yu, X. Wang, X. Lu, and C. Zhu, “A Semi-Supervised Speech Deception Detection Algorithm Combining Acoustic Statistical Features and Time-Frequency Two-Dimensional Features,” Brain Sci, vol. 13, no. 5, pp. 1–22, May 2023, doi: 10.3390/brainsci13050725.

P. C. Loizou, “SPEECH ENHANCEMENT Theory and Practice Second Edition,” 2013.

Saeed V. Vaseghi, P. Rayner, B. Milner, C. Ho, and A. Chen, “Advanced Digital Signal Processing and Noise Reduction,” 2000.

D. Y. Mohammed, P. J. Duncan, M. M. Al-Maathidi, and F. F. Li, “A system for semantic information extraction from mixed soundtracks deploying MARSYAS framework,” in Proceeding - 2015 IEEE International Conference on Industrial Informatics, INDIN 2015, Institute of Electrical and Electronics Engineers Inc., Sep. 2015, pp. 1084–1089. doi: 10.1109/INDIN.2015.7281886.

Theodoros Giannakopoulos and Aggelos Pikrakis, “AUDIO ANALYSIS: A MATLAB Approach,” 2014. Accessed: Mar. 15, 2023. [Online]. Available: htpp://booksite.elsevier.com/9780080993881

H. Jeon, Y. Jung, S. Lee, and Y. Jung, “Area-efficient short-time fourier transform processor for time–frequency analysis of non-stationary signals,” Applied Sciences (Switzerland), vol. 10, no. 20, pp. 1–10, Oct. 2020, doi: 10.3390/app10207208.

D. Yehya Mohammed, “OVERLAPPED SPEECH AND MUSIC SEGMENTATION USING SINGULAR SPECTRUM ANALYSIS AND RANDOM FORESTS,” Manchester ,School of Computing, Science and Engineering University of Salford, 2017.

M. B. Er, “A Novel Approach for Classification of Speech Emotions Based on Deep and Acoustic Features,” IEEE Access, 2020, doi: 10.1109/ACCESS.2020.3043201.

A. Koduru, H. B. Valiveti, and A. K. Budati, “Feature extraction algorithms to improve the speech emotion recognition rate,” Int J Speech Technol, vol. 23, no. 1, pp. 45–55, Mar. 2020, doi: 10.1007/s10772-020-09672-4.

Homayoon Beigi, “Fundamentals of Speaker Recognition,” Yorktown Heights ,NY , USA, 2011. doi: 10.1007/978-0-387-77592-0.

A. Zheng and A. Casari, “Feature Engineering for Machine Learning PRINCIPLES AND TECHNIQUES FOR DATA SCIENTISTS,” 2018.

Downloads

Published

2024-03-01

How to Cite

K. Al-Dhaher, F., Y. Mohammed, D., & Khalaf , M. (2024). The Most Important Features of Lie Detection Using Voice Stress . Al-Iraqia Journal for Scientific Engineering Research, 3(1), 93–110. https://doi.org/10.58564/IJSER.3.1.2024.149

Issue

Section

Articles