Kates J M
Center for Research in Speech and Hearing Sciences, City University of New York, New York 10036, USA.
J Acoust Soc Am. 1995 Jul;98(1):172-80. doi: 10.1121/1.413753.
A neural net is a "black box" information processing system that can be used for pattern matching, optimal prediction, or functional approximation. A neural net requires a minimal amount of a priori knowledge about the problem to be solved, but can require large amounts of data to converge to a solution. For a hearing-aid fitting procedure, a multilayer perceptron net was trained to generate an optimum match between a set of input pure-tone audiograms and the corresponding best frequency response and gain for each subject. The feasibility of using neural nets to select hearing-aid response characteristics was tested using both simulated and real audiometric data. The simulation results indicate that a neural net can be successfully trained to reproduce a fitting rule such as the NAL-R procedure, and that a minimum of about 50 sets of audiometric response data are needed for the net to converge to a generalized solution. When used to predict, from the pure-tone audiograms, the best frequency response characteristics determined for subjects having severe-to-profound hearing losses, the neural net was more accurate than the NAL-R fitting procedure derived from the same data.
神经网络是一种“黑箱”信息处理系统，可用于模式匹配、最优预测或函数逼近。神经网络解决问题所需的先验知识极少，但可能需要大量数据才能收敛到一个解决方案。对于助听器选配程序，训练了一个多层感知器网络，以便在一组输入纯音听力图与每个受试者相应的最佳频率响应和增益之间生成最佳匹配。使用模拟和实际听力测量数据测试了利用神经网络选择助听器响应特性的可行性。模拟结果表明，可以成功训练神经网络以重现诸如NAL-R程序之类的选配规则，并且网络要收敛到一个通用解决方案至少需要约50组听力测量响应数据。当用于根据纯音听力图预测重度至极重度听力损失受试者的最佳频率响应特性时，神经网络比从相同数据得出的NAL-R选配程序更准确。
