PSO-BP Neural Network Based Speech Recognition Research

Speech recognition technology has a very important application in the field of machine learning. Based on the use of BP neural network to recognize ten English words, this paper uses particle swarm algorithm to optimize the weights and thresholds of BP neural network to solve the problem of neural network weights easily falling into local extreme values. The simulation results show that the improved neural network has higher prediction accuracy and faster convergence speed, which improves the generalization ability of the neural network to a certain extent.