A keyword spotter which incorporates neural networks for secondary processing

Experiments using restricted Coulomb energy (RCE) and backward error propagation trained artificial neural networks (ANNs) for secondary processing in a keyword spotting application are described. Several types and configurations of neural networks are explored, including single, multiple, and hybrid networks. Several feature space transformations are used to permit the ANNs to examine the potential word in several time-invariant formats. The best performance is obtained using a multiple RCE network structure, which improves performance an average of 5% over a range of false alarm rates. The effectiveness of several ANNs as feature extraction mechanisms and as pattern classifiers is discussed relative to the keyword spotting problem. Issues pertaining to the complexity and required training time of the ANN structures are discussed