Department of Speech, Language and Hearing Sciences, The University of Texas at Austin, Austin, Texas 78712, USA.
School of Mathematical and Statistical Sciences, The University of Texas Rio Grande Valley, Edinburg, Texas 78539, USA.
J Acoust Soc Am. 2023 Oct 1;154(4):2278-2288. doi: 10.1121/10.0021303.
Some individuals complain of listening-in-noise difficulty despite having a normal audiogram. In this study, machine learning is applied to examine the extent to which hearing thresholds can predict speech-in-noise recognition among normal-hearing individuals. The specific goals were to (1) compare the performance of one standard (GAM, generalized additive model) and four machine learning models (ANN, artificial neural network; DNN, deep neural network; RF, random forest; XGBoost; eXtreme gradient boosting), and (2) examine the relative contribution of individual audiometric frequencies and demographic variables in predicting speech-in-noise recognition. Archival data included thresholds (0.25-16 kHz) and speech recognition thresholds (SRTs) from listeners with clinically normal audiograms (n = 764 participants or 1528 ears; age, 4-38 years old). Among the machine learning models, XGBoost performed significantly better than other methods (mean absolute error; MAE = 1.62 dB). ANN and RF yielded similar performances (MAE = 1.68 and 1.67 dB, respectively), whereas, surprisingly, DNN showed relatively poorer performance (MAE = 1.94 dB). The MAE for GAM was 1.61 dB. SHapley Additive exPlanations revealed that age, thresholds at 16 kHz, 12.5 kHz, etc., on the order of importance, contributed to SRT. These results suggest the importance of hearing in the extended high frequencies for predicting speech-in-noise recognition in listeners with normal audiograms.
一些人尽管听力图正常，但仍会抱怨在噪声环境中听声困难。在这项研究中，我们应用机器学习来检验听力阈值在多大程度上可以预测正常听力个体在噪声环境中的言语识别能力。具体目标是：(1) 比较一种标准模型（广义相加模型，GAM）和四种机器学习模型（人工神经网络，ANN；深度神经网络，DNN；随机森林，RF；极端梯度提升，XGBoost）的性能；(2) 检验个体听力测试频率和人口统计学变量在预测噪声环境中的言语识别能力方面的相对贡献。本研究的档案数据包括听力阈值（0.25-16 kHz）和言语识别阈值（SRT；n = 764 名参与者或 1528 只耳朵；年龄 4-38 岁）。在机器学习模型中，XGBoost 的表现明显优于其他方法（平均绝对误差，MAE = 1.62 dB）。ANN 和 RF 的表现相似（MAE 分别为 1.68 和 1.67 dB），而令人惊讶的是，DNN 的表现相对较差（MAE = 1.94 dB）。GAM 的 MAE 为 1.61 dB。SHapley Additive exPlanations 揭示了年龄、16 kHz、12.5 kHz 等频率的阈值，按重要性顺序，对 SRT 有贡献。这些结果表明，在听力图正常的个体中，扩展高频听力对预测噪声环境中的言语识别能力非常重要。
