The Study And Realization Of The Chinese Speech Recognition For Robot

It is of great importance to study practical control of robot,with Chinese speech recognition to its widely application.This paper studies the application of Chinese speech recognition in the robot,s control,it puts forward uses TMS32OVC5416DSK signal process broad as technology plate,realizes a robot,s control system with Chinese speech recognition.This paper improvens and optimizes the method to consist of part of speech recognition,it confirms the pre-processor of speech signal,the arithmetic of port detect, the arithmetic of pick up character vector and the leading technology of today speech recognition—Hidden Markov Model,carries out through training and recognizing to model.In the meantime,it adopts Linear Prediction Cepstrum Coefficients very difference ponderance and Mel Cepstrum Cofficients very difference ponderance to separate by way of character vector of speech signal to found system,besides comparing the recognizing capability of two systems.Experiment proves,that it obtains the better recognizing effect with the instance of speech templet of multi-people training and recognizing the system.The recognizing ratio and real-time quality of two system can satisfy the practical need of speech recognition for service robot.In comparison under the same condition,the recognizing ratio of system that uses LPCMCC as character parameter of speech signal is better than that use of using LPCC.At the same time,the word list the system is easy to change and expand,with the increase of training stylebook,the recognizing ratio will be improved and apply to many application situation.The system of speech recognition that this paper sets up and realizes can service not only robot,but also establish the foundation of studying more complex and practical system of speech recognition for robot.