相空间重构在语音情感识别中的研究

Speech emotion recognition based on phase space reconstruction

为了更为全面地表征语音情感状态,弥补线性情感特征参数在刻画不同情感类型上的不足,将相空间重构理论引入语音情感识别中来,通过分析不同情感状态下的混沌特征,提取Kolmogorov熵和关联维作为新的情感特征参数,并结合传统语音特征使用支持向量机(SVM)进行语音情感识别。实验结果表明,通过引入混沌参数,与传统物理特征进行识别的方案相比,准确率有了一定的提高,为语音情感的识别提供了一个新的研究途径。

In order to express the sound emotion state totally, make up the inadequate of emotional conventional linear argument at depicting different types of character sentiments, this paper takes the phase space reconstruction theory into the sound emotional identification, by analyzing chaotic features on the different sound emotional states, proposes correlation dimension and Kolmogorov entropy as emotional characteristic parameters, combines with traditional voice acoustic features and uses Support Vector Machine（SVM）for speech emotion recognition. The results show that recognition accuracy is improved through using chaotic characteristic parameters, providing a new research approach for speech emotion recognition.