| 矢量量化与神经网络相结合的说话人识别系统 |
| |
| 引用本文： | 李战明,王贞. 矢量量化与神经网络相结合的说话人识别系统[J]. 计算机工程与应用, 2006, 42(15): 204-206,230 |
| |
| 作者姓名： | 李战明 王贞 |
| |
| 作者单位： | 兰州理工大学电气工程与信息工程学院,兰州,730050;兰州理工大学电气工程与信息工程学院,兰州,730050 |
| |
| 摘 要： | 介绍了说话人识别系统的基本概念,在分析了传统VQ模型与神经网络模型的基础上,提出了一种VQ与神经网络相结合的说话人识别系统模型。通过提取出的特征参数(MFFC),建立系统模型,实验证明了该模型性能随着时间的变化有较好的稳定性。
|
| 关 键 词： | 说话人识别 矢量量化 神经网络 特征提取 |
| 文章编号： | 1002-8331-（2006）15-0204-03 |
| 收稿时间： | 2005-09-01 |
| 修稿时间： | 2005-09-01 |
A Speaker Recognition System Using Vector Quantization Combined with Neural Network |
| |
| Li Zhanming,Wang Zhen. A Speaker Recognition System Using Vector Quantization Combined with Neural Network[J]. Computer Engineering and Applications, 2006, 42(15): 204-206,230 |
| |
| Authors: | Li Zhanming Wang Zhen |
| |
| Affiliation: | College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050 |
| |
| Abstract: | Basic conception of a speaker recognition system is presented.Based on studying traditional VQ modeal and Neural network model,a speaker recognition system using VQ combined with neural network is proposed.After extracting feature parameter(MFCC),a system model is established.The experiment results show that this system possesses a stable quality along with the time varying. |
| |
| Keywords: | speaker recognition vector quantization neural networks feature extraction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
