摘要
为有效提高语音情感识别系统的识别正确率,提出一种基于SVM的语音情感识别算法。该算法提取语音信号的能量、基音频率及共振峰等参数作为情感特征,采用SVM(Support Vector Machine,支持向量机)方法对情感信号进行建模与识别。在仿真环境下的情感识别实验中,所提算法相比较人工神经网络的ACON(All Class in one Network,"一对多")和OCON(One class in one network,"一对一")方法识别正确率分别提高了7.06%和7.21%。实验结果表明基于SVM的语音情感识别算法能够对语音情感信号进行较好地识别。
In order to improve recognition accuracy of the speech emotion recognition system effectively,a speech emotion recognition algorithm based on SVM is proposed.In the proposed algorithm,some parameters extracted from speech signals,such as： energy,pitch frequency and formant,are used as emotional features.Furthermore,an emotion recognition model is established with SVM method.Simulation environment experiential results reveal that the recognition ratio of the proposed algorithm obtains the relative increasing of 7.06% and 7.21% compared with artificial neural networks such as ACON（All Class in one Network,＂one to many＂） and OCON（One class in one network,＂one to one＂） methods.The result of the experiment shows that the speech emotion recognition algorithm based on SVM can improve the performance of the emotion recognition system effectively.
出处
《计算机系统应用》
2011年第5期87-91,共5页
Computer Systems & Applications
基金
安徽省自然科学基金(090412261X)
博士点基金(200803570002)
