| 改进的HMM和小波神经网络的抗噪语音识别 |
| |
| 引用本文： | 肖勇,覃爱娜. 改进的HMM和小波神经网络的抗噪语音识别[J]. 计算机工程与应用, 2010, 46(22): 162-164. DOI: 10.3778/j.issn.1002-8331.2010.22.048 |
| |
| 作者姓名： | 肖勇 覃爱娜 |
| |
| 作者单位： | 中南大学 信息科学与工程学院，长沙 410083 |
| |
| 摘 要： | 通过MFFC计算出的语音特征系数，由于语音信号的动态性，帧之间有重叠，噪声的影响，使特征系数不能完全反映出语音的信息。提出一种隐马尔可夫模型（HMM）和小波神经网络（WNN）混合模型的抗噪语音识别方法。该方法对MFCC特征系数利用小波神经网络进行训练，得到新的MFCC特征系数。实验结果表明，在噪声环境下，该混合模型比单纯HMM具有更强的噪声鲁棒性，明显改善了语音识别系统的性能。
|
| 关 键 词： | 隐马尔可夫模型 小波神经网络 鲁棒性 特征系数 |
| 收稿时间： | 2009-01-09 |
| 修稿时间： | 2009-4-13 |
Noise robust speech recognition based on improved hidden Markov model and wavelet neural network |
| |
| XIAO Yong,QIN Ai-na. Noise robust speech recognition based on improved hidden Markov model and wavelet neural network[J]. Computer Engineering and Applications, 2010, 46(22): 162-164. DOI: 10.3778/j.issn.1002-8331.2010.22.048 |
| |
| Authors: | XIAO Yong QIN Ai-na |
| |
| Affiliation: | College of Information Science and Technology，Central South University，Changsha 410083，China |
| |
| Abstract: | The feature coefficients based on MFCC are not fully reflecting speech information as a result of speech signal movement and overlap of frames, especially noisy effect.A new method for noise robust speech recognition based on a hy- brid rnodel of Hidden Markov Models（HMM） and Wavelet Neural Network（WNN） is presented.The model trained by this method is used in MFCC coefficients.Experimental results show this model has better noise robustness. |
| |
| Keywords: | Hidden Markov Models（HMM） Wavelet Neural Network（WNN） robustness feature coefficients |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
