专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明公开

EP4121910A1 AN ARTIFICIAL INTELLIGENCE SYSTEM FOR CAPTURING CONTEXT BY DILATED SELF-ATTENTION 有权
公开(公告)号：EP4121910A1
公开(公告)日：2023-01-25
申请号：EP21840193.3
申请日：2021-11-30
申请人： Mitsubishi Electric Corporation
发明人： MORITZ, Niko , HORI, Takaaki , LE ROUX, Jonathan
IPC分类号： G06N3/04 , G10L21/00

62. 发明公开

EP4038606A1 LONG-CONTEXT END-TO-END SPEECH RECOGNITION SYSTEM 有权
公开(公告)号：EP4038606A1
公开(公告)日：2022-08-10
申请号：EP21732592.7
申请日：2021-04-28
申请人： Mitsubishi Electric Corporation
发明人： HORI, Takaaki , MORITZ, Niko , HORI, Chiori , LE ROUX, Jonathan
IPC分类号： G10L15/16

63. 发明授权

EP3292515B1 METHOD FOR DISTINGUISHING ONE OR MORE COMPONENTS OF SIGNAL 有权
公开(公告)号：EP3292515B1
公开(公告)日：2020-08-19
申请号：EP16759889.5
申请日：2016-07-05
申请人： Mitsubishi Electric Corporation
发明人： HERSHEY, John , LE ROUX, Jonathan , WATANABE, Shinji , CHEN, Zhuo
IPC分类号： G06N99/00 , G10L21/0272

64. 发明公开

EP3292515A1 METHOD FOR DISTINGUISHING ONE OR MORE COMPONENTS OF SIGNAL 有权
标题翻译：用于区分一个或多个信号分量的方法
公开(公告)号：EP3292515A1
公开(公告)日：2018-03-14
申请号：EP16759889.5
申请日：2016-07-05
申请人： Mitsubishi Electric Corporation
发明人： HERSHEY, John , LE ROUX, Jonathan , WATANABE, Shinji , CHEN, Zhuo
IPC分类号： G06N99/00 , G10L21/0272
摘要： A method distinguishes components of an acoustic signal by processing the signal to estimate a set of analysis features, wherein each analysis feature defines an element of the signal and has feature values that represent parts of the signal, processing the signal to estimate input features of the signal, and processing the input features using a deep neural network to assign an associative descriptor to each element of the signal, wherein a degree of similarity between the associative descriptors of different elements is related to a degree to which the parts of the signal represented by the elements belong to a single component of the signal. The the similarities between associative descriptors are processed to estimate correspondences between the elements of the signal and the components in the signal. Then, the signal is processed using the correspondences to distinguish component parts of the signal.

65. 发明公开

EP3175393A1 METHOD FOR TRANSFORMING INPUT SIGNALS 有权
标题翻译：转换输入信号的方法
公开(公告)号：EP3175393A1
公开(公告)日：2017-06-07
申请号：EP15751113.0
申请日：2015-07-24
申请人： Mitsubishi Electric Corporation
发明人： HERSHEY, John , LE ROUX, Jonathan , WENINGER, Felix
IPC分类号： G06N3/04 , G06N3/08
CPC分类号： G06N3/0445 , G06N3/0436 , G06N3/08 , G06N3/084 , G06N7/005 , G06N99/005 , G10L15/16
摘要： A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trined to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.
摘要翻译：一种用于变换输入信号的方法，通过首先定义用于变换输入信号的模型，其中该模型由约束和一组模型参数来指定。迭代推理过程从该模型和该组模型参数导出并且展开成一组层，其中该过程的每次迭代有一个层，并且其中所有层使用相同的一组网络参数。通过解开一组网络参数形成神经网络，使得每层有一组网络参数，并且每组网络参数可单独维护并分别适用于相应的层。训练神经网络以获得训练的神经网络，然后使用训练的神经网络对输入信号进行变换以获得输出信号。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式