CAJ | 학술논문

针对数字音乐语音情感识别问题，提出一种基于特征差异度和SVM投票机制进行识别的方法。该方法不仅降低了特征向量的维度，而且保留了足够的能够描述数字音乐语音不同情感之间差异的特征。同时，该方法利用多个二分SVM分类器进行投票，减少了每个分类器的权重，从而降低了误差。实验结果表明，该方法能够有效地提高识别准确率。
침대수자음악어음정감식별문제，제출일충기우특정차이도화SVM투표궤제진행식별적방법。해방법불부강저료특정향량적유도，이차보류료족구적능구묘술수자음악어음불동정감지간차이적특정。동시，해방법이용다개이분SVM분류기진행투표，감소료매개분류기적권중，종이강저료오차。실험결과표명，해방법능구유효지제고식별준학솔。
To solve emotion recognition problem for digital music speech, an emotion recognition method which is based on difference between characteristics and SVM voting mechanism is proposed. The method not only reduces the dimension of feature vectors, but retains the characteristics between different emotions of digital music speech.Meanwhile, using multiple two-class SVM classifier to vote for digital music speech, the method decreases the weight of each classifier and reduces the error. The experimental results show that this method can effectively improve the recognition accuracy.