基于区分加权干扰属性投影的语种识别方法  

Language Recognition Based on Discriminating Weighted Nuisance Attribute Projection

作　　者：刘伟伟[1] 吉立新[1] 李邵梅[1] 何赞园[1] 

机构地区：[1]解放军信息工程大学信息工程学院,河南郑州450002

出　　处：《中文信息学报》2012年第6期59-64,共6页Journal of Chinese Information Processing

基　　金：国家863计划重点资助项目(2011AA010603)

摘　　要：传统NAP,投影矩阵的训练需要繁杂的参数调整和大量的标注语料,投影后不能彻底去除干扰信息且会造成一定的信息损失。为此,该文提出一种DWNAP算法,首先通过统计各语种训练语音协方差矩阵的特征值离散度,对干扰源进行量化估计,利用规整的估计值作为各语种的区分性权重参与投影矩阵的训练。汉日英三种语言的测试结果表明,相对于传统NAP提出的DWNAP有效地提高了系统识别性能,EER相对降低了7.51%。The conventional NAP＇s training method of projection matrix requires laborious parameter tuning process over the training corpus with information labels. It cannot remove all unwanted information and result in loss of de- sirable information. To tackle these problems, a discriminating weighted nuisance attribute projection （DWNAP） is proposed in this paper. DWNAP quantitatively estimates the source of nuisance based on the normalized scatter of the given language＇s eigenvalues for discriminating weighting in training of projection matrix. Experiments on Chinese, Japanese and English show the advantage of the proposed DWNAP, with a relative reduction in the equal error rate （EER） for about 7.51% compared with the traditional NAP.

关 键 词：语种识别 失配补偿 区分加权干扰属性投影 干扰属性投影 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]