The authors describe several experiments in which the use of artificial neural networks (ANNs) for the continuous speech speaker-independent keyword recognition problem was investigated. They discuss methodologies for reducing a primary keyword spotting system's susceptibility to false alarms while maintaining recognition accuracy. The keyword spotter uses a conventional dynamic time warping algorithm to detect the start- and end-point of each potential keyword. The ANNs serve as a secondary processing stage for this segmented utterance. The ANNs attempt to classify this utterance by formulating the recognition problem as a pattern matching problem. In the hybrid network experiments, the utterance was processed into features derived from the activation at the hidden layer of a back-propagation trained network. Hybrid representations were grouped with two other feature representations in a multiple neural network system. A recognition accuracy of 78% on the Stonehenge X database was obtained while rejecting 72% of the false alarms which were detected by the primary keyword spotting system.>

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.>