| 实时说话人辨识系统中改进的DTW算法 |
| |
| 引用本文： | 李邵梅,刘力雄,陈鸿昶. 实时说话人辨识系统中改进的DTW算法[J]. 计算机工程, 2008, 34(4): 218-219 |
| |
| 作者姓名： | 李邵梅 刘力雄 陈鸿昶 |
| |
| 作者单位： | 国家数字交换系统工程技术研究中心,郑州,450002 |
| |
| 摘 要： | 识别正确率和抗噪性能是语音识别的研究重点，而识别响应速度也是决定系统实用化的关键。文章改进了传统的动态时间弯折算法结构，将其应用于实时说话人辨识系统中，极大地提高了系统运行速度，随着待识别语音数目的增多，该算法优势更加明显。实验表明，在不影响系统识别率的情况下，该方法使系统的运行速度平均提高了1.5倍。
|
| 关 键 词： | 说话人辨识 美尔倒谱系数 动态时间弯折 |
| 文章编号： | 1000-3428（2008）04-0218-02 |
| 收稿时间： | 2007-03-29 |
| 修稿时间： | 2007-03-29 |
Improved DTW Algorithm in Real-time Speaker Identification System |
| |
| LI Shao-mei,LIU Li-xiong,CHEN Hong-chang. Improved DTW Algorithm in Real-time Speaker Identification System[J]. Computer Engineering, 2008, 34(4): 218-219 |
| |
| Authors: | LI Shao-mei LIU Li-xiong CHEN Hong-chang |
| |
| Affiliation: | (National Digital Switching System Research Center, Zhengzhou 450002) |
| |
| Abstract: | Response rate of recognition is a key factor for a speech recognition system as well as recognition correct rate and noise robust property. This paper improves the conventional DTW algorithm’s structure, and fastens the running speed in real-time speaker identification. The advantage of the new algorithm is more obvious with the increment of speeches. Experiments show that the method can increase the operation speed by 1.5 times. |
| |
| Keywords: | speaker identification Mel-frequency Cepstral Coefficient(MFCC) Dynamic Time Warping(DTW) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载免费的PDF全文 |
