DISTANCE MEASURES FOR SPEECH PROCESSING
DISTANCE MEASURES FOR SPEECH PROCESSING
复制标题
DOI：
10.1109/tassp.1976.1162849
复制
发表时间：
1976-01-01
期刊：
影响因子：
--
通讯作者：
MARKEL, JD
中科院分区：
文献类型：
--
作者：
GRAY, AH;MARKEL, JD
从理论和实验两个方面讨论了语音处理中四种距离度量的性质和相互关系。考虑了均方根(RMS)对数谱距离、倒谱距离、似然比(最小残差原理或增量编码(Delco)算法)和COSH度量(基于两个非对称似然比)。结果表明，倒谱测度自下而上限定均方根对数谱测度，而COSH测度自上而下限定均方根对数谱测度。结果表明，似然比的一个简单的非线性变换与期望范围内的均方根对数谱测量高度相关。还考虑了距离测量值和感知之间的关系。似然比、倒谱度量和COSH度量很容易从线性预测滤波系数递归地估计，并且每一个都具有有意义且相互关联的频域解释。给出了计算递归计算距离度量的Fortran程序。
The properties and interrelationships among four measures of distance in speech processing are theoretically and experimentally discussed. The root mean square (rms) log spectral distance, cepstral distance, likelihood ratio (minimum residual principle or delta coding (DELCO) algorithm), and a cosh measure (based upon two nonsymmetrical likelihood ratios) are considered. It is shown that the cepstral measure bounds the rms log spectral measure from below, while the cosh measure bounds it from above. A simple nonlinear transformation of the likelihood ratio is shown to be highly correlated with the rms log spectral measure over expected ranges. Relationships between distance measure values and perception are also considered. The likelihood ratio, cepstral measure, and cosh measure are easily evaluated recursively from linear prediction filter coefficients, and each has a meaningful and interrelated frequency domain interpretation. Fortran programs are presented for computing the recursively evaluated distance measures.