Deceptive Chinese speech detection based on sparse decomposition of cepstral feature  

作　　者：FAN Xiaohe ZHAO Heming CHEN Xueqin ZHOU Yan 

机构地区：[1]Electronic Information Institute of Soochow University [2]College of Electronic Information Engineering,Suzhou Vocational University

出　　处：《Chinese Journal of Acoustics》2019年第1期99-112,共14页声学学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(61372146);the Natural Science Foundation of Jiangsu Province(BK20131196);the youth found of Natural Science Foundation of Jiangsu Province(BK20160361)

摘　　要：In order to improve the performance of deception detection based on Chinese speech signals, a method of sparse decomposition on spectral feature is proposed. First, the wavelet packet transform is applied to divide the speech signal into multiple sub-bands. Band cepstral features of wavelet packets are obtained by operating the discrete cosine transform on loga?rithmic energy of each sub-band. The cepstral feature is generated by combing Mel Frequency Cepstral Coefficient and Wavelet Packet Band Cepstral Coefficient. Second, K-singular value decomposition algorithm is employed to achieve the training of an over-complete mixture dictionary based on both the truth and deceptive feature sets, and an orthogonal matching pursuit algorithm is used for sparse coding according to the mixture dictionary to get sparse feature.Finally, recognition experiments axe performed with various classified modules. Experimental results show that the sparse decomposition method has better performance comparied with con?ventional dimension reduced methods. The recognition accuracy of the method proposed in this paper is 78.34%, which is higher than methods using other features, improving the recognition ability of deception detection system significantly.In order to improve the performance of deception detection based on Chinese speech signals, a method of sparse decomposition on spectral feature is proposed. First, the wavelet packet transform is applied to divide the speech signal into multiple sub-bands. Band cepstral features of wavelet packets are obtained by operating the discrete cosine transform on logarithmic energy of each sub-band. The cepstral feature is generated by combing Mel Frequency Cepstral Coefficient and Wavelet Packet Band Cepstral Coefficient. Second, K-singular value decomposition algorithm is employed to achieve the training of an over-complete mixture dictionary based on both the truth and deceptive feature sets, and an orthogonal matching pursuit algorithm is used for sparse coding according to the mixture dictionary to get sparse feature.Finally, recognition experiments are performed with various classified modules. Experimental results show that the sparse decomposition method has better performance comparied with conventional dimension reduced methods. The recognition accuracy of the method proposed in this paper is 78.34%, which is higher than methods using other features, improving the recognition ability of deception detection system significantly.

关 键 词：CEPSTRUM features VOICE DETECTION Chinese SPEECH SIGNAL 

分 类 号：O4[理学—物理]