摘要
介绍了基于连续隐含马尔可夫模型(CHMM)的非特定人孤立词语音识别系统。根据分析该系统计算复杂度,提出了一系列的优化方法,通过MATLAB平台下的研究实验数据表明,优化后的语音识别系统与传统CHMM语音识别系统对比,计算时间是传统CHMM系统的9.97%,而识别率仅从传统CHMM系统的94%下降到91.3%。
Speaker-independent isolated-word recognition system based on Continuous HMM is presented. This paper analyzed the computational complexity of the system. A series of optimized way is suggested to reduce the computation complexity. The experimental data based on MATLAB platform show that, the computation time of the optimized speech recognition system is 9.97 % of the traditional CHMM speech recognition systems,and the recognition accuracy is degraded only from 94 % to 91.3 %.
