The Research Of Speech Recognition System Bascd On SPCE061A Microcomtioler

Since human being can make various machines and use them, the people have had an ideal that various machines could understand their language, and act according to their orally orders, thereby realizing the linguistic communion between the human and the machine. With the unceasing development of the technology, and the appearance of Speech Recognition Technology, the ideal of human being has realized. The Speech Recognition Technology is a high technology, which make the machine change the speech signals into homologous text or order by recognition and comprehend. The speech recognition is a cross-subject, and it is becoming to the key-technology of human-computer interface in information technology. The combination of speech recognition and speech synthesis make man can operate the computer through the speech order without the keyboard. The application of speech recognition has become a rising competitive high technology industry. Today, the products of speech recognition have already taken up more and more proportion in the application of human-computer interaction.At present, according as the difference of hard core, the research of Speech Recognition System includes: the Speech Recognition System using PC as its hare core and the embedded Speech Recognition System using special chip. The research in the text is the embedded Speech Recognition System based on SPCE061A Microcontroller.On the base of introducing the development of the Embedded Speech Recognition System in domestic and overseas and the theory of speech recognition, the article introduce one Microcontroller which fit to processing speech-LINGYANG SPCE061A microchip and its application in the Speech Recognition System .According as the principle with low-cost and nicer performance, the system has accomplished the following work:l.The system selects one kind Microcontroller as its hard core, which includes 16-bit MCU, A/D, AGC, 2KRAM, 32KFlash, PWM and DSP function. In the design of hardware it has realized the collection of speech signals, the memory of speech signals, the processing of speech signals, the play of speech signals and the lighting control etc.2.The system adopts linear-prediction cepstral coefficients with little account quantity as characteristic vectors, and adopts the distance Hidden Markov Model technique with high recognition efficiency to recognize the speech signals. Then the system has high recognitionspeed and high recognition efficiency. The system is also able to recognize accurately even in the environment with louder noises.S.The Speech Recognition System not only has high recognition veracity, small volume, economization for power consumption, low cost and high reliability, but also has high operation speed and the realization of real-time speech recognition. Furthermore, in the system, the function of speech cue offers a favorable interface for human-computer interaction.All these characteristics embody fully the predominance of the embedded speech recognition.4.On the base of the process of speech exercitation, the system can realize the speech recognition of special people and the dialogue between man and machine. If it could make more improvement on these bases, the system would realize the speech recognition of common people and be more consummate-...