A combinational method for Robust Speech Recognition Using Microphone Array and Neural Network

This paper describes use of integrated systems of microphone arrays and neural networks for robust speech recognition in variable acoustic environments, where the user must not be encumbered by microphone equipments. Speech recognition systems can operate best for "high-quality closetalking speech."However when the acoustical, articulator, or phonetic characteristics of speech in the training and testing environments differ, Performance of the recognizers is typically decreased by environmental interference and mismatch in training conditions and testing conditions. It is found that use of microphone arrays and neural network processors can increase the performance of existing speech recognizers in an adverse acoustic environment, thus avoiding the need to retrain the recognizer, a complex and tedious task. We also present results showing that a system of microphone array and neural network can achieve a higher word recognition accuracy in an unmatched training/testing condition than that obtained with a retrained speech recognizer using array speech for both training and testing, i.e., a matched training/testing condition.