Datum M S, Palmieri F, Moiseff A
Engineering Technology Center, Mystic, Connecticut 06355-1208, USA.
J Acoust Soc Am. 1996 Jul;100(1):372-83. doi: 10.1121/1.415854.
A three-layer neural network is used to estimate the direction of a sound source from the signals detected by two directional, spatially separate receivers. Although the implemented system does not require any specific knowledge about acoustical parameters or propagation properties, a model of the acoustical environment is used to generate simulated data for training the network. The neural network is trained according to the multiple extended Kalman algorithm (MEKA), which provides fast convergence and does not require intervention for adjustment of the learning parameters. Lower bounds on estimation are computed and compared with simulations using the neural network.
一个三层神经网络用于根据两个定向的、空间上分离的接收器检测到的信号来估计声源的方向。虽然所实现的系统不需要关于声学参数或传播特性的任何特定知识，但使用声学环境模型来生成用于训练网络的模拟数据。该神经网络根据多重扩展卡尔曼算法（MEKA）进行训练，该算法提供快速收敛且不需要干预来调整学习参数。计算估计的下限，并与使用神经网络的模拟结果进行比较。
