Automatic lie detection method and system based on domain adversarial training

Abstract

The invention discloses an automatic lie detection method and system based on domain adversarial training, and the method comprises the steps: S1, multi-modal feature extraction: extracting text feature representation, audio feature representation and facial feature representation; S2, performing multi-modal feature fusion, and obtaining multi-modal feature representation by using an adaptive attention mechanism; S3, performing time sequence modeling, and capturing context information in the dialogue by using a bidirectional recurrent neural network to assist lie detection of the current sentence; S4, performing domain adversarial training, extracting lie feature representation irrelevant to speakers by using a domain adversarial network, and reducing the influence of speaker difference onautomatic lie detection performance; S5, predicting a lie level, and inputting to-be-tested data into the lie classifier subjected to domain adversarial training for predicting the lie level of the individual. The system comprises a multi-modal feature extraction module, a multi-modal feature fusion module, a time sequence modeling module, a domain adversarial training module and a lie level prediction module which are sequentially connected from top to bottom.

Description

technical field [0001] The invention relates to the technical field of lie analysis, in particular to a method and system for automatically predicting individual lie levels by encoding video information. Background technique [0002] "Lying" refers to the speaker's behavior of deliberately concealing and providing language information that does not match the facts on the premise of knowing the facts. Automatic lie detection refers to proposing corresponding models and methods based on the psychological and behavioral reflections of the subjects to establish the ability of the machine to capture clues of lies. Automatic lie detection has broad prospects in the field of criminal investigation, and can help criminal investigators speed up interrogation and improve interrogation efficiency. [0003] Although automatic lie detection has great practical significance, there are still many difficulties. First of all, it is difficult to label lie data. How to use less sample data t...

AI Technical Summary

Problems solved by technology

However, the above method cannot guarantee that the model will be able to learn the speaker-independent lie features.

Images