Based Hmm Speech Recognition Algorithm And Fpga Hardware Implementation

With the development of information science and voice technology, inter- communication with computer by using voice have been a symbol of modern scientific achievements, that also made speech recognition a research direction of modern information science.Speech recognition technology is concerned with many research fields of varied subject, they have contributed a lot to the development of speech recognition. Now the mainstream of Speech recognition technology is base on the basic theory of statistic mode recognition.The purpose of this article is to realize a isolated word recognition system, this article detailedly introduce the basic conception, common method and character of isolated word speech recognition , and particularly discuss the procedure of gain eigenvector, the principle and critical problems of HMM. An embedded speaker-independent isolated word speech recognition system is realized and improved in the Xilinx Virtex-II Pro FPGA platform.With the help of a modified real time voice activity detection algorithm (VAD)based on the log.Energy acceleration associated with voice onset, we only perform feature extraction and decoding to the active voice and ignore the frames of non-activity.Test on 150 words vocabulary shows that system provides a recognition accuracy rate of 97.3%using only 1.42 times of real time. Giving an implementation solution of embedded real time system based on FPGA development platform.