一种基于贪婪策略的说话人语音特征优选方法  

A Method of Speaker Acoustic Features Optimal Selection Based on Greedy Strategy

作　　者：陈觉之[1] 张贵荣 周宇欢[3] 

机构地区：[1]海军指挥学院信息系 [2]92601部队计量站 [3]解放军理工大学指挥信息系统学院

出　　处：《计算机与现代化》2013年第5期201-205,共5页Computer and Modernization

基　　金：江苏省自然科学基金资助项目(BK2009059);解放军理工大学预研基金资助项目(2009TX08)

摘　　要：为了提高说话人识别的性能,提出一种语音特征优选方法,从目前使用效果较好的特征参数中,采用贪婪算法优选出若干维特征用于识别。在TIMIT语音数据库上实验显示,识别率相比传统方法提高了1.6%;对于加入了噪声的语音,识别率提高了6%,识别速度提高了5倍左右。实验结果表明,优选后的特征参数能够去除不良特征对识别系统的干扰,有效提高说话人识别系统的识别率和识别速度。In order to improve the performance of speaker recognition, a method for optimal speaker acoustic features sdection is proposed, using greedy algorithm to select some dimensional features from a large dimensional feature set in turn. The recognition rate is increased by 1.6% on pure voice than traditional method and by 6% on noisy voice, the recognition speed is increased about 5 times in experiments based on TIMIT. The experiment results show that the optimal selective features which eliminate disturbance of other redundant features can effectively improve both the recognition accuracy and the computational speed on the speaker recognition system.

关 键 词：说话人识别 特征选择 高斯混合模型 贪婪算法 美尔倒谱系数 

分 类 号：TN912.34[电子电信—通信与信息系统]