CAJ | 학술논문

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。
위료경위전면지표정어음정감상태，미보선성정감특정삼수재각화불동정감류형상적불족，장상공간중구이론인입어음정감식별중래，통과분석불동정감상태하적혼돈특정，제취Kolmogorov적화관련유작위신적정감특정삼수，병결합전통어음특정사용지지향량궤（SVM）진행어음정감식별。실험결과표명，통과인입혼돈삼수，여전통물리특정진행식별적방안상비，준학솔유료일정적제고，위어음정감적식별제공료일개신적연구도경。
In order to express the sound emotion state totally, make up the inadequate of emotional conventional linear argu-ment 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.