首页>
外国专利>
device for pattern recognition with a neural network model for kontextabhaengige columns
device for pattern recognition with a neural network model for kontextabhaengige columns
展开▼
机译:神经网络模型用于kontextabhaengige列的模式识别设备
展开▼
页面导航
摘要
著录项
相似文献
摘要
A pattern (for example speech) recognition device comprising an artificial neural network set-up having K X M output units and provided for calculating probabilities of observing a feature vector (xt) (12) on a class (qk) (1 /= k /= K) (11) conditioned on predetermined contextual models (cm) (1 /= m /= M) (17), each of said classes being represented by at least one model belonging to a finite set of models (M) governed by statistical laws. Said neural network set-up is splitted into a first neural network having K output units and being provided for calculating a posteriori probabilities of said class (qk) given said observed vector (xt), and at least one further neural network having M output units and provided for calculating a posteriori probabilities of said contextual models, conditioned on said class.
展开▼
机译:一种模式(例如语音)识别设备,包括具有KXM输出单元的人工神经网络设置,用于计算在类(qk)(1 = k <上)上观测特征向量(xt)(12)的概率/ = K)(11)以预定的上下文模型(cm)(1 = m = M)(17)为条件,每个所述类由至少一个属于有限模型集(M )受统计法管辖。所述神经网络装置被分成具有K个输出单元的第一神经网络,并被提供用于在给定所述观测矢量(xt)的情况下计算所述类别(qk)的后验概率,以及至少一个另外的具有M个输出单元的神经网络。并且提供了以所述类别为条件来计算所述上下文模型的后验概率。
展开▼