Refining algorithmic estimation of relative fundamental frequency: Accounting for sample characteristics and fundamental frequency estimation method.
Refining algorithmic estimation of relative fundamental frequency: Accounting for sample characteristics and fundamental frequency estimation method.
复制标题
DOI：
10.1121/1.5131025
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Jennifer M. Vojtech;Roxanne K. Segina;Daniel P. Buckley;Katharine R. Kolin;Monique C Tardif;J. Noordzij;C. Stepp
中科院分区：
文献类型：
--
作者：
Jennifer M. Vojtech;Roxanne K. Segina;Daniel P. Buckley;Katharine R. Kolin;Monique C Tardif;J. Noordzij;C. Stepp
相对基频 (RFF) 是一种很有前途的评估声音障碍的声学测量方法。然而，当前 RFF 算法的准确性在各种声音信号中都存在差异。作者研究了基频 (fo) 估计和样本特征如何影响手动和半自动 RFF 估计之间的关系。声学记录收集自 227 名患有声音障碍的人和 256 名没有声音障碍的人。将常见的 fo 估计技术与 RFF 算法中当前实现的自相关方法进行了比较。使用训练集（1158 个样本）构建基于音调强度的类别，并针对每个类别调整算法阈值。然后使用特定类别阈值在独立测试集（291 个样本）上计算 RFF，并通过平均偏差误差 (MBE) 和均方根误差 (RMSE) 与手动 RFF 进行比较。用于 fo 估计的 Auditory-SWIPE 与手动 RFF 具有最大的对应性，并且与特定类别的阈值一起实施。与未修改的算法（MBE = 0.90 ST，RMSE = 0.34 ST）相比，改进估计和考虑样本特征导致与手动 RFF [MBE = 0.01 半音 (ST)，RMSE = 0.28 ST] 的对应性增加，半自动 RFF 估计的 MBE 和 RMSE 分别减少了 88.4% 和 17.3%。
Relative fundamental frequency (RFF) is a promising acoustic measure for evaluating voice disorders. Yet, the accuracy of the current RFF algorithm varies across a broad range of vocal signals. The authors investigated how fundamental frequency (fo) estimation and sample characteristics impact the relationship between manual and semi-automated RFF estimates. Acoustic recordings were collected from 227 individuals with and 256 individuals without voice disorders. Common fo estimation techniques were compared to the autocorrelation method currently implemented in the RFF algorithm. Pitch strength-based categories were constructed using a training set (1158 samples), and algorithm thresholds were tuned to each category. RFF was then computed on an independent test set (291 samples) using category-specific thresholds and compared against manual RFF via mean bias error (MBE) and root-mean-square error (RMSE). Auditory-SWIPE' for fo estimation led to the greatest correspondence with manual RFF and was implemented in concert with category-specific thresholds. Refining fo estimation and accounting for sample characteristics led to increased correspondence with manual RFF [MBE = 0.01 semitones (ST), RMSE = 0.28 ST] compared to the unmodified algorithm (MBE = 0.90 ST, RMSE = 0.34 ST), reducing the MBE and RMSE of semi-automated RFF estimates by 88.4% and 17.3%, respectively.