倒谱参数稀疏分解下的汉语音谎言检测

Deceptive Chinese speech detection based on sparse decomposition of cepstral feature

为了提高汉语语音的谎言检测准确率,提出了一种对信号倒谱参数进行稀疏分解的方法。首先,采用小波包滤波器组对语音信号进行多频带划分,求得子频带对数能量并进行离散余弦变换以提取小波包频带倒谱系数,结合梅尔频率谱系数得到倒谱参数;其次,依据K-奇异值分解方法分别利用说谎和非说谎两种状态下的语音倒谱参数集训练得到过完备混合字典,在此字典上根据正交匹配追踪算法对参数集进行稀疏编码提取稀疏特征;最终进行多种分类模型下的识别实验·实验结果表明,稀疏分解方法相比传统参数降维方法具有更好的优化性能,本文推荐的稀疏谱特征最佳识别率达到78.34%,优于其他特征参数,显著提高了谎言检测识别准确率。

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, wavelet package transform is applied to divide the speech signal into multiple sub-bands, and the band cepstral feature of wavelet packet are obtained by operating discrete cosine transform on logarithmic of each sub-band energy, and cepstral feature is generated by combing Mel Frequency Cepstral Coefficient and Wavelet Packet Band Cepstral Coefficient. Then K-singular value decomposition algorithm is employed to achieve the training over-complete mixture dictionary based on both truth and deceptive feature sets, and orthogonM 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 than conventional dimension reduced method. The recognition accuracy of the sparse cepstral features proposed in this paper is 78.34% higher than other features, improving the recognition ability of deception detection system significantly.