用DSP技术开发的一种新的语音识别系统

A New Speech Recognition System with DSP

本文介绍了一种基于听觉谱特征参数的语音识别方法和系统．该系统采用高速ＤＳＰ芯片ＴＭＳ３２０Ｃ２５，实现了语音信号的实时处理．用由此芯片开发的ＥＩＳＡ插卡与计算机结合，构成了一个智能化语音输入实时识别系统．实验结果表明，在小词汇量特定人条件下，该系统的正识率可达到９８％以上，在非特定人和有噪情况下，系统正识率分别为９５％和９０％以上．通过比较发现，该系统在正识率。

A new speech recognition system based on auditory spectrum feature parameters is presented in this paper. The TMS320C25 DSP chip is used to construct a EISA board and a real time speech recognition system is thus developed. Experiments show that the accuracy of the system is as high as 98% in the speaker dependent condition. In speaker independent and noisy condition, the accuracy is 95% and 90%. It is proved that the new method has higher accuracy and better robustness than the traditional one.