A Semi-Supervised Lie Detection Algorithm Based on Integrating Multiple Speech Emotional Features

Author:

Xi Ji1,Yu Hang2,Xu Zhe1,Zhao Li3,Tao Huawei2

Affiliation:

1. School of Computer Information Engineering, Changzhou Institute of Technology, Changzhou 213022, China

2. Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology, Zhengzhou 450001, China

3. School of Information Science and Engineering, Southeast University, Nanjing 210096, China

Abstract

When people tell lies, they often exhibit tension and emotional fluctuations, reflecting a complex psychological state. However, the scarcity of labeled data in datasets and the complexity of deception information pose significant challenges in extracting effective lie features, which severely restrict the accuracy of lie detection systems. To address this, this paper proposes a semi-supervised lie detection algorithm based on integrating multiple speech emotional features. Firstly, Long Short-Term Memory (LSTM) and Auto Encoder (AE) network process log Mel spectrogram features and acoustic statistical features, respectively, to capture the contextual links between similar features. Secondly, the joint attention model is used to learn the complementary relationship among different features to obtain feature representations with richer details. Lastly, the model combines the unsupervised loss Local Maximum Mean Discrepancy (LMMD) and supervised loss Jefferys multi-loss optimization to enhance the classification performance. Experimental results show that the algorithm proposed in this paper achieves better performance.

Funder

Science and Technology Plan Project of Changzhou

Natural Science Foundation of the Jiangsu Higher Education Institutions of China

Henan Province Key Scientific Research Projects Plan of Colleges and Universities

Publisher

MDPI AG

Reference23 articles.

1. Viji, D., Gupta, N., and Parekh, K.H. (2022). History of Deception Detection Techniques. Proceedings of International Conference on Deep Learning, Computing and Intelligence: ICDCI 2021, Springer Nature Singapore.

2. Review of emotional feature extraction and dimension reduction method for speech emotion recognition;Liu;Chin. J. Comput.,2017

3. Invited article: Face, voice, and body in detecting deceit;Ekman;J. Nonverbal Behav.,1991

4. Kirchhuebel, C. (2013). The Acoustic and Temporal Characteristics of Deceptive Speech. [Ph.D. Thesis, University of York].

5. Feature analysis and neural network-based classification of speech under stress;Hansen;IEEE Trans. Speech Audio Process.,1996

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3