专利内容由知识产权出版社提供
专利名称：NEURAL NETWORK-BASED LOUDSPEAKER
MODELING WITH A DECONVOLUTIONFILTER
发明人：Ajay Iyer,Douglas J. Button申请号：US15099433申请日：20160414
公开号：US20170303039A1公开日：20171019
专利附图：
摘要：A technique for controlling a loudspeaker system with an artificial neuralnetwork includes filtering, with a deconvolution filter, a measured system response of a
loudspeaker and a reverberant environment in which the loudspeaker is disposed togenerate a filtered response, wherein the measured system response corresponds to anaudio input signal applied to the loudspeaker while the loudspeaker is disposed in thereverberant environment. The techniques further include generating, via a neural networkmodel, an initial neural network output based on the audio input signal, comparing theinitial neural network output to the filtered response to determine an error value, andgenerating, via the neural network model, an updated neural network output based onthe audio input signal and the error value.
申请人：Harman International Industries, Incorporated
地址：Stamford CT US
国籍：US
更多信息请下载全文后查看