摘要
说话人识别技术的研究是智能信息处理的研究热点问题之一。支持向量机是统计学习理论的一个重要学习方法,也是解决模式识别问题的一个有力工具。介绍了模式识别的分类原理,提出基于支持向量机的说话人识别模型。通过把所得到的结果与原有VQ模型的试验结果相比较,表明该方法具有较高的识别准确率。
The study of speaker identification is one of the ad hoc problems in the investigation of intelligence information. Support Vector Machine （SVM） is an important learning method of statistical learning theory,and is also a powerful tool for pattern recognition. In this paper,we introduce the theory of SVM, and then propose a speaker identification model based on SVM. By comparing the results obtained in this paper with those known in terms of the VQ model,it is shown that the method presented in this paper has a better performance in the identification accuracy than traditional method.
出处
《现代电子技术》
2007年第6期125-127,共3页
Modern Electronics Technique
基金
辽宁省教育厅教育与发展规划项目(2004F099)
