基于Legendre正交分解的源-目标说话人声门波导数转换  

Glottal Flow Derivative Conversion from Source Speaker to Target Speaker Based on Legendre Orthogonal Decomposition

作　　者：孙俊[1] 于俊朋[1] 戴蓓蒨[2] 

机构地区：[1]南京电子技术研究所,江苏南京210013 [2]中国科学技术大学电子与科学技术系,安徽合肥230027

出　　处：《小型微型计算机系统》2009年第5期1021-1024,共4页Journal of Chinese Computer Systems

基　　金：江苏省六大人才高峰高层次人才项目(08-E-008-)资助

摘　　要：使用一种不需要精确的声门关闭期间(GCI)信息便可求出声门波的方法,该方法通过在一个基音同步帧中搜索到一个最平滑的线性预测分析逆滤波的残差信号,从而得到一个没有激励影响的声道参数,间接的获得了GCI,因而可以获得比较精确的声门波导数波形.在此基础上提出了一种基于勒让德正交多项式的声门波导数参数提取方法,将声门波导数波形的n维勒让德正交空间的坐标组成一个特征矢量作相应转换,此方法去除了特征矢量中各维参数间的相关性,并且矢量间的欧氏距离表示了声门波导数波形间的相似度,因而聚类及其转换效果要优于多项式特征参数.在微软语音库上作的相关一系列对比实验表明,相对于多项式拟合系数特征参数基于VQ码本映射方法的基准系统,本文提出的方法的帧平均互相关系数提高了11.92%.An automated glottal waveform estimation algorithm which does not need to estimate the precise glottal closure information （GCI） is used. The algorithm uses only basic approximations of glottal closure regions and successive iterations to f-rod the best candidate for a glottal waveform estimate within a speech frame. To parameterize the glottal flow derivative, we propose a novel method which employs the n-dimensional Legendre orthogonal coefficients to form a vector describing the shape of glottal flow derivative. This method eliminates the relativity among each dimension within the vector. More over, Euclidian distance between two vectors just reveals the similarity of their shapes, thus performance of proposed method is better than normal polynomial coefficients. Compared with normal polynomial coefficients based VQ conversion algorithm, the performance of proposed approach is improved by 11.92%.

关 键 词：声音转换 声门波导数 多项式拟合 勒让德正交多项式 

分 类 号：TP912.3[自动化与计算机技术]