Tanner Kristine, Roy Nelson, Ash Andrea, Buder Eugene H
Department of Communication Disorders, The University of Utah, Salt Lake City, Utah 84112-0252, USA.
J Voice. 2005 Jun;19(2):211-22. doi: 10.1016/j.jvoice.2004.02.005.
Voice clinicians require an objective, reliable, and relatively automatic method to assess voice change after medical, surgical, or behavioral intervention. This measure must be sensitive to a variety of voice qualities and severities, and preferably should reflect voice in continuous speech. The long-term average spectrum (LTAS) is a fast Fourier transform-generated power spectrum whose properties can be compared with a Gaussian bell curve using spectral moments analysis. Four spectral moments describe features of the LTAS: Spectral mean (Moment 1) and standard deviation (Moment 2) represent the spectrum's central tendency and dispersion, respectively. Skewness (based on Moment 3) and kurtosis (based on Moment 4) represent the spectrum's tilt and peakedness, respectively. To examine whether the first four spectral moments of the LTAS were sensitive to perceived voice improvement after voice therapy, this investigation compared pretreatment and posttreatment voice samples of 93 patients with functional dysphonia using spectral moments analysis. Inspection of the results revealed that spectral mean and standard deviation lowered significantly with perceived voice improvement after successful behavioral management (p < 0.001). However, changes in skewness and kurtosis were not significant. Furthermore, lowering of the spectral mean uniquely accounted for approximately 14% of the variance in the pretreatment to posttreatment changes observed in perceptual ratings of voice severity (p < 0.001), indicating that spectral mean (ie, Moment 1) of the LTAS may be one acoustic marker sensitive to improvement in dysphonia severity.
嗓音临床医生需要一种客观、可靠且相对自动的方法，来评估医学、手术或行为干预后的嗓音变化。这种测量方法必须对各种嗓音质量和严重程度敏感，并且最好能反映连续语音中的嗓音情况。长期平均谱（LTAS）是一种通过快速傅里叶变换生成的功率谱，其特性可通过谱矩分析与高斯钟形曲线进行比较。四个谱矩描述了LTAS的特征：谱均值（矩1）和标准差（矩2）分别代表频谱的集中趋势和离散程度。偏度（基于矩3）和峰度（基于矩4）分别代表频谱的倾斜度和峰值度。为了研究LTAS的前四个谱矩是否对嗓音治疗后感知到的嗓音改善敏感，本研究使用谱矩分析比较了93例功能性发声障碍患者治疗前和治疗后的嗓音样本。结果检查显示，在成功的行为管理后，随着感知到的嗓音改善，谱均值和标准差显著降低（p < 0.001）。然而，偏度和峰度的变化并不显著。此外，谱均值的降低唯一地解释了在嗓音严重程度的感知评分中观察到的治疗前到治疗后变化中约14%的方差（p < 0.001），这表明LTAS的谱均值（即矩1）可能是一个对发声障碍严重程度改善敏感的声学标志物。
