The Small-Vocabulary Speech Recognition System Based On DSP

With the development of Speech Recognition technique and the software and hardware for Digital Signal Processing in recent years, the research of speech recognition and control system have been more and more attended. Although there still exist many problems which need to be overcome such as the technique of large-vocabulary, speaker-independent, continuous speech recognition, the technique (LPC and DTW) for small-vocabulary, speaker-dependent, isolated-word speech recognition has come to the age of maturity.In the paper, I first present a simple introduction of the history and the current status of the research and application of speech recognition technique, and point out the signification about our work.. Small-vocabulary speech recognition system based on DSP is intellectualized system relied on special industrial conditions, We can forecast that the system can be used at the task of monitoring and controlling at locale on the conditon of improving recognition rate, such as the task of monitoring and controlling the oil well and oil tank at abominable conditions of the desert oil field.In the theory introduction part, after simply introduces the basis knowledge of voice signal, a systemic and concise brief of the preceding disposal, endpoint detection, parameter pick-up and matching-method of speech recognition according the basic framework of speech recognition system are given.At the aspect of application in the control field of small-vocabulary, speaker-dependent, isolated-word speech recognition technology, it explains the research of the speech recognition and control system . The used methods and functions of chips that TMS320VC5402 and MC14LC5480 are discussed in details in the paper.Next, I present the design steps of DSP system and complied with the design steps I present the research work of speech recognition DSP system which is based on the theory of speech recognition and the used methods and functions of chips.To come true small-vocabulary speech recognition system on the DSP chip by the research about speech recognition theory and arithmetic. The result indicates that this method is feasible. At last, to bring forward expectation for the further research..