An artificial neural network for sound localization using binaural cues
An artificial neural network for sound localization using binaural cues
复制标题
DOI：
10.1121/1.415854
复制
发表时间：
1996-07-01
影响因子：
2.4
通讯作者：
Moiseff, A
中科院分区：
文献类型：
--
作者：
Datum, MS;Palmieri, F;Moiseff, A
一个三层的神经网络被用来估计声源的方向，从两个方向，空间上分离的接收器检测到的信号。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，但是声学环境的模型用于生成用于训练网络的模拟数据。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并且不需要干预来调整学习参数。估计的下限计算和使用神经网络的模拟比较。(C)1996年美国声学学会。
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. (C) 1996 Acoustical Society of America.