系統(tǒng)采用凌陽(yáng)SPCE061A 單片機(jī)作為語(yǔ)音識(shí)別系統(tǒng)的主控芯片。通過(guò)硬件電路
設(shè)計(jì)和軟件代碼部分成功的設(shè)計(jì)并實(shí)現(xiàn)了一種具有語(yǔ)音識(shí)別功能、語(yǔ)音提示(語(yǔ)音合成)及語(yǔ)音回放(語(yǔ)音編碼記錄)功能的嵌入式語(yǔ)音識(shí)別系統(tǒng)。語(yǔ)音識(shí)別模型采用（DHMM)離散隱馬爾可夫模型，利用Baum-welth 重估算法、前向后向算法、viterbi 算法來(lái)完成語(yǔ)音模板的訓(xùn)練和語(yǔ)音識(shí)別的任務(wù)。
關(guān)鍵詞：SPCE061A 單片機(jī)；語(yǔ)音識(shí)別系統(tǒng)；語(yǔ)音識(shí)別模型
Design of Speech Recognition System Base on SPCE061A Yingfeng fengyufen Abstract: The system selects SPCE061A as MCU of speech recognition system. Through the hardware circuit design and the software code, design and realize the embedded speech recognition system which contains functions of speech recognition, voice prompt (speech synthesis) and audio playback (speech coding record). The discrete hidden markov model(DHMM)is adopted，Baum-Welth reestimation algorithm, forward-backward procedure and viterbi algorithm is utilized to train and recognize the speech signal.
Keywords: SPCE061A MCU; Speech Recognition System; Speech Recognition Model