Neural network noisy speech recognition and understanding with information feedback

The paper is about the noisy speech recognition and understanding. It adopts the two level modular Extended Associative Memory Neural Networks: (EAMNN) for speech recognition, information feedback of the linguistic constraint reasoning and statistic inference for understanding processing. Recognition part consists of two levels, the first level EAMNN classifies the input date into category groups, and the second level branch module EAMNN classifies input data into a specified category. The learning speed of two level modular EAMNNs is 9 times faster than conventional BP net, it has a high adaptive, robust, fault tolerance and associative memory ability for noisy speech signal. The understanding part extracts speech recognition word candidates and predict inference nest word according to statistic inference base, the linguistic rule and syntax base will reduce the candidates and acoustic recognition errors, then compare and correct error, and guide nest speech processing by using information feedback, to realize recognition of sentence.