基于模糊多类支持向量机的声母识别方法  

Application of Consonant Recognition Based on Fuzzy Multi-Class Support Vector Machines

作　　者：赵剑辉[1] 凌卫新[1] 陈卓铭[2] 何敏聪[1] 欧阳静明[2] 

机构地区：[1]华南理工大学理学院,广东广州510640 [2]暨南大学附属第一医院语言障碍中心,广东广州510630

出　　处：《计算机工程与科学》2011年第5期160-164,共5页Computer Engineering & Science

基　　金：国家863计划资助项目(2007AA02Z482);广州市重大攻关资助项目(2007C13G0131);中央高校基本科研业务费专项资金资助(21610507)

摘　　要：声母识别在构音障碍评估中有重要临床意义,而声母时长短、不平稳,传统方法的识别效果不理想。本文使用小波变换对声母信号进行多尺度分析,提取出新的声母特征向量(DWTMFC-CT),可以更精细刻画相似声母的差别,然后利用模糊多类支持向量机进行声母的识别。为降低模糊支持向量机进行多分类时所带来的计算复杂度,使用两阶段算法。实验结果表明,本文算法不仅提高了模糊支持向量机的训练效率,同时对声母有较好的分类效果。Consonant recognition has important clinical significance in the assessment of dysarthria,while the consonants are so short and unstable that the recognition results of the traditional methods are ineffective.The algorithm described in this paper extracts a new feature（DWTMFC-CT） of the consonants employing wavelet transformation.And the difference of similar consonants can be described more accurately by the feature.And then the algorithm classifies consonants using a multi-class fuzzy support vector machine（FSVM）.In order to reduce the computation complexity caused by using the standard fuzzy support vector machines for multi-class classification,this paper proposes an algorithm based on two stages.The experimental results show that the proposed algorithm can get better classification results while reducing the training time greatly.

关 键 词：声母识别 模糊支持向量机 小波变换 MEL倒谱系数 

分 类 号：TN912.34[电子电信—通信与信息系统]