| 基于小波分析和HMM的语音识别模型建立与仿真 |
| |
| 引用本文： | 张丽,王福忠,张涛. 基于小波分析和HMM的语音识别模型建立与仿真[J]. 计算机与现代化, 2007, 0(9): 72-75 |
| |
| 作者姓名： | 张丽 王福忠 张涛 |
| |
| 作者单位： | 河南理工大学电气工程与自动化学院,河南,焦作,454003 |
| |
| 摘 要： | 利用隐马尔可夫模型HMM优异的时序建模能力及小波变换可以对信号进行多尺度分析并有效提取信号的局部信息的特点,建立了混合语音识别模型.在语音信号的识别过程中考虑到了信号的非平稳性,采用并行识别的方法分别获取分类信息,根据混合模型的识别算法做出识别决策,减小了系统对环境的依赖性,提高了其自适应能力.仿真实验结果表明,混合模型识别结果比单一HMM模型或小波模型识别结果更佳,提高了整体的识别速度和识别率.
|
| 关 键 词： | 语音识别 隐马尔可夫模型(HMM) 小波分析 鲁棒性 小波分析 语音识别模型 仿真实验 Wavelet Analysis Based Model Speech Recognition Simulation 识别率 识别速度 小波模型 结果 适应能力 依赖性 环境 系统 决策 识别算法 混合模型 分类信息 |
| 文章编号： | 1006-2475（2007）09-0072-04 |
| 收稿时间： | 2007-04-29 |
| 修稿时间： | 2007-04-29 |
Establishment and Simulation of Speech Recognition Model Based on Wavelet Analysis and HMM |
| |
| ZHANG Li,WANG Fu-zhong,ZHANG Tao. Establishment and Simulation of Speech Recognition Model Based on Wavelet Analysis and HMM[J]. Computer and Modernization, 2007, 0(9): 72-75 |
| |
| Authors: | ZHANG Li WANG Fu-zhong ZHANG Tao |
| |
| Affiliation: | School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China |
| |
| Abstract: | Applying dynamic time sequence modeling ability of hidden Markov model(HMM) and extracting more effectively the local information of Wavelet transform,the paper presents a hybrid speech recognition model.In the process of identifying the voice signal,considering nonstationarity of phonetic signal,parallel identification methods are used to obtain classified information,the result of recognition is made by using recognition algorithm of the hybrid model,which reduces the system's dependence on the environment and improves its adaptive capacity.Recognition experiment shows that this hybrid model has higher performance than hidden Markov model in noisy speech recognition. |
| |
| Keywords: | speech recognition hidden Markov model Wavelet analysis robust |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
