论文部分内容阅读
语音情感识别日益受到人们的关注，在社会生活中发挥着重要作用。为了提高语音情感的识别率，提出一种改进的灰狼算法优化支持向量机的分类模型（IGWO-SVM）。首先介绍了灰狼算法（GWO）的基本理论；然后嵌入选择算子和引入非线性收敛因子来提升IGWO的寻优性能；最后采用IGWO优化SVM参数，进而建立语音情感的分类模型。通过10个基准测试函数的仿真实验，验证了IGWO性能优于GWO。对于参比模型，IGWO-SVM模型能够有效提高语音情感的识别率。
Voice emotion recognition has attracted more and more attention and plays an important role in social life. In order to improve the recognition rate of speech emotion, an improved gray wolf algorithm is proposed to classify the support vector machine (IGWO-SVM). Firstly, the basic theory of Gray Wolf algorithm (GWO) is introduced. Then the selection operator and non-linear convergence factor are embedded to improve the performance of IGWO. Finally, IGWO is used to optimize the SVM parameters, and then a classification model of speech emotion is established. The simulation of 10 benchmark functions verified that IGWO outperformed GWO. For the reference model, IGWO-SVM model can effectively improve the recognition rate of speech emotion.