CAJ | 학술논문

针对语音情感线性参数在刻画不同情感类型特征上的不足，将多重分形理论引人语音情感识别中．通过分析不同语音情感状态下的多重分形特征，提取多重分形谱参数和广义hurst指数作为新的语音情感特征参数，并结合传统语音声学特征，采用支持向量机SVM对其进行语音情感识别．试验结果表明，该方法可使系统的准确率和稳定性得到有效提高．非线性参数的引人为语音情感识别提供了一个新的思路．
침대어음정감선성삼수재각화불동정감류형특정상적불족，장다중분형이론인인어음정감식별중．통과분석불동어음정감상태하적다중분형특정，제취다중분형보삼수화엄의hurst지수작위신적어음정감특정삼수，병결합전통어음성학특정，채용지지향량궤SVM대기진행어음정감식별．시험결과표명，해방법가사계통적준학솔화은정성득도유효제고．비선성삼수적인인위어음정감식별제공료일개신적사로．
In order to overcome the inadequacy of emotional conventional linear argument at depicting different types of character sentiments,this paper takes the multiple fractals theory into the sound emotional identify,by analyzing the multiple fractal features on the different sound emotional state, and proposes multifractal spectrum parameters and generalized hurst index as emotional conventional parameters, combined with traditional voice acoustic features and using support vector machine （SVM） for speech emotion recognition. The resuits show that the accuracy and stability of the recognition system are ira. proved effectively through using non-linear parameters, compared with using the linear features of traditional voice recognition method. It provides a new idea for voice emotion recognition.