| 改进的混合MFCC语音识别算法研究 |
| |
| 引用本文： | 袁正午,肖旺辉. 改进的混合MFCC语音识别算法研究[J]. 计算机工程与应用, 2009, 45(33): 108-110. DOI: 10.3778/j.issn.1002-8331.2009.33.035 |
| |
| 作者姓名： | 袁正午 肖旺辉 |
| |
| 作者单位： | 重庆邮电大学,中韩合作GIS研究所,重庆,400065;重庆大学,土木工程学院博士后流动站,重庆,400045;重庆邮电大学,中韩合作GIS研究所,重庆,400065 |
| |
| 基金项目： | 国家高技术研究发展计划(863) |
| |
| 摘 要： | 针对MFCC特征参数在语音识别中对中高频信号的识别精度不高的特点，提出采用IMFCC，MIDMFCC，MFCC相结合的改进算法，使用混合滤波器组，提高在语音中高频区域中的识别精度。实验结果表明，改进之后的算法与经典算法比较，在相同环境下对语音信息的识别率都有一定程度的提高。
|
| 关 键 词： | Mel频率倒谱系数(MFCC) 语音识别 特征提取 |
| 收稿时间： | 2009-06-15 |
| 修稿时间： | 2009-8-4 |
Improved speech recognition algorithm based on MFCC feature |
| |
| YUAN Zheng-wu,XIAO Wang-hui. Improved speech recognition algorithm based on MFCC feature[J]. Computer Engineering and Applications, 2009, 45(33): 108-110. DOI: 10.3778/j.issn.1002-8331.2009.33.035 |
| |
| Authors: | YUAN Zheng-wu XIAO Wang-hui |
| |
| Affiliation: | 1.Sino-Korea GIS Research Center，Chongqing University of Posts & Telecommunications，Chongqing 400065，China 2.Civil Engineering Mobile Station for Post Doctors，Chongqing University，Chongqing 400045，China |
| |
| Abstract: | Aiming at low calculation accuracy of MFCC feature parameters for speech recognition in high-frequency signals,this paper adopts the combination algorithm of IMFCC,MIDMFCC,MFCC,whieh uses a mixture of filter banks to enhance high-fre-quency calculation accuracy in the calculation accuracy.The experiments result shows that the recognition rate of improved algo-rithm increases compared to the classical algorithm in the same environment. |
| |
| Keywords: | Mel-Frequency Cepstral Coefficients(MFCC) speech recognition feature extraction |
| 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 |
