Research And Realization Of Automobile Speech Recognition System Based On DSP

With the development of speech recognition technique and the rapid development of DSP chips and computer technique in recent years, the require of real time deal system to speech can be achive . the research of speech recognition and control system have been more and more attended to. The speech recognition technology has been applied to the industry control, communication, and consumption area broadly. Speech is the most convenient and common tool in exchanging information for people , as well as for machine.Base on popularization of car , car become the most important and populare traffic tool. Therefore, the research of the speech recognition is real meaningful and filled wide prospects of the application fields.Using the speech recognition technology in the car, automobile recognition system is more real significance.The research subject in this paper is the voice control system based on DSP in car, which is aimed for the isolated word recognition and in order to achieve speech recoginition and voice control device in the car.The project do some work in the improving algorithm of voice recognition, design of system of voice recognition, hardware design and software programming.The domestic and international development of the voice recognition technology is firstly analysed and the background of research along with the significance is elaborated. On the basis of the above, the basic theory of voice recognition is introduced according to the model of voice recognition system, which includes the voice signals' pretreatment and the detection of endpoint. Comparing the traditional method of detection, this paper proposes a double threshold comparative method. The feature is extracted and it is focus on the inverted pedigree of LPC and Mel scale frequency. The voice recognition algorithm DTW and HMM is introduced and analyzed in the paper. The improved DTW algorithms is proposed,applying of finding most matching path in the method of moving L area.Followed by the analysis about DSP from TI, it proposes the corresponding design method of voice recognition system referring to the existed mature theory foundation.Convert the digital signals from A/D converter of voice signal to the DSP for processing and recognition,the results of recognition were output to follow-up control circuit realized by CPLD ,The signal processing module, voice acquisition module, expanded memory module,CPLD control module and power module are specially designed in this paper.In the software algorithms, Double Threshold Comparative method is applied in the detection of endpoint and and take the Mel cepstrum coefficient as the speech feature parameter. In addition, the Dynamic Time Warping (DTW) is adopted, comparing DTW and HMM and thinking the feature of our system.The building circumstance of system is researched, basing on which, the design and debug of the program is completed and proves the feasibility of algorithm. The optimization of program is also researched.Finally the full text is summarized and it points out the future work and the direction to he researched.