Askenfelt A G, Hammarberg B
J Speech Hear Res. 1986 Mar;29(1):50-64. doi: 10.1044/jshr.2901.50.
The performance of seven acoustic measures of cycle-to-cycle variations (perturbations) in the speech waveform was compared. All measures were calculated automatically and applied on running speech. Three of the measures refer to the frequency of occurrence and severity of waveform perturbations in special selected parts of the speech, identified by means of the rate of change in the fundamental frequency. Three other measures refer to statistical properties of the distribution of the relative frequency differences between adjacent pitch periods. One perturbation measure refers to the percentage of consecutive pitch period differences with alternating signs. The acoustic measures were tested on tape recorded speech samples from 41 voice patients, before and after successful therapy. Scattergrams of acoustic waveform perturbation data versus an average of perceived deviant voice qualities, as rated by voice clinicians, are presented. The perturbation measures were compared with regard to the acoustic-perceptual correlation and their ability to discriminate between normal and pathological voice status. The standard deviation of the distribution of the relative frequency differences was suggested as the most useful acoustic measure of waveform perturbations for clinical applications.
对语音波形中七个逐周期变化(扰动)的声学指标的性能进行了比较。所有指标均自动计算并应用于连续语音。其中三个指标涉及语音特定选定部分中波形扰动的出现频率和严重程度,这些部分通过基频变化率来识别。另外三个指标涉及相邻音高周期之间相对频率差异分布的统计特性。一个扰动指标指的是具有交替符号的连续音高周期差异的百分比。这些声学指标在41名嗓音患者成功治疗前后的录音语音样本上进行了测试。给出了声学波形扰动数据与嗓音临床医生评定的感知异常嗓音质量平均值的散点图。对这些扰动指标在声学 - 感知相关性以及区分正常和病理性嗓音状态的能力方面进行了比较。相对频率差异分布的标准差被认为是临床应用中最有用的波形扰动声学指标。