本文首先介绍了目前语音识别的发展现状和主要手段，分析了语音识别中所采用的主要特征参数和比较前沿的研究方向，另外着重讲解了语音识别中最常用隐马尔可夫H(MM)模型，及应用广泛的矢量量化方法(VQ)。接着介绍了嵌入式平台，从软、硬件方面着重介绍了与语音识别相关部分的设计包括硬件及相关驱动程序设计，最后介绍了系统实现方法与测试结果。

-This paper describes the current status of the development of speech recognition and the main means of analysis used in speech recognition parameters and compare the main features cutting-edge research, while focused on explaining the most commonly used in speech recognition, Hidden Markov H (MM) model of , and the widely used vector quantization (VQ). Then introduced the embedded platform, from hardware and software aspects of highlighting the relevant parts of speech recognition with the design, including hardware and associated drivers for the design, finally introduced a system implementation method and test results.