Convolutional Bidirectional Long Short-Term Memory for Deception Detection With Acoustic Features

IEEE Access

卷:6

Yue Xie¹  Li Zhao¹  Yue Zhu¹  Ruiyu Liang²  Huawei Tao³ 

[1] Laboratory of Underwater Acoustic Signal Processing, Southeast University, Nanjing, China;

[2] School of Communication Engineering, Nanjing Institute of Technology, Nanjing, China;

[3] School of Information Science and Engineering, Henan University of Technology, Zhengzhou, China;

关键词: Deception detection;    long short-term memory;    variable dimension;    acoustic features;   

DOI  :  10.1109/ACCESS.2018.2882917

来源: DOAJ

【 摘 要 】

Despite the widespread use of multi-physiological parameters for deception detection, they have been severely restricted due to the high degree of cooperation in contacting-detection. Therefore, a noncontacting method is proposed for deception detection using acoustic features as an input and convolutional bidirectional long short-term memory (LSTM) as a classifier. The algorithm extracts frame-level acoustic features whose dimension dynamically varies with the length of speech, in order to preserve the temporal information in the original speech. Bidirectional LSTM was applied to match temporal features with variable dimension in order to learn the context dependences in speech. Furthermore, the convolution operation replaces multiplication in the traditional LSTM, which is used to excavate time-frequency mixed data. The average accuracy of the experiment on Columbia-SRI-Colorado corpus reaches 70.3%, which is better than the previous works with non-contacting modes.

【 授权许可】

Unknown