A Speech Recognition Based on Quantum Neural Networks Trained by IPSO

Aimed at PSO´s defect of prematurity, an improved particle swarm optimization(IPSO) is presented. The new arithmetic has better optimization performance by adding random data to premature particles´ speed and position. It was applied to the parameter learning and training of Quantum Neural Network(QNN), and a higher efficiency speech recognition system which based on IPSO-QNN was established. The experimental results of MATLAB simulation showed that the new arithmetic did a better job in speech recognition rate and speed which make the best of faster quantum neural computation and PSO´s global optimization ability.