| 一种基于子带处理的PAC说话人识别方法研究 |
| |
| 引用本文： | 陈迪,何静媛,李战明.一种基于子带处理的PAC说话人识别方法研究[J].计算机仿真,2008,25(3):306-309. |
| |
| 作者姓名： | 陈迪 何静媛 李战明 |
| |
| 作者单位： | 兰州理工大学电气工程与信息工程学院,甘肃,兰州,730050 |
| |
| 摘 要： | 目前,说话人识别系统对于干净语音已经达到较高的性能,但在噪声环境中,系统的性能急剧下降.一种基于子带处理的以相位自相关(PAC)系数及其能量作为特征的说话人识别方法,即宽带语音信号经Mel滤波器组后变为多个子带信号,对各个子带数据经DCT变换后提取PAC系数作为特征参数,然后对每个子带分别建立HMM模型进行识别,最后在识别概率层中将HMM得出的结果相结合之后得到最终的识别结果.实验表明,该方法在不同信噪比噪声和无噪声情况下的识别性能都有很大提高.
|
| 关 键 词： | 子带 相位自相关 能量 说话人识别 |
| 文章编号： | 1006-9348(2008)03-0306-03 |
| 修稿时间： | 2007年2月4日 |
Speaker Recognition Using PAC Based on Sub-band Processing |
| |
| CHEN Di,HE Jing-yuan,LI Zhan-ming.Speaker Recognition Using PAC Based on Sub-band Processing[J].Computer Simulation,2008,25(3):306-309. |
| |
| Authors: | CHEN Di HE Jing-yuan LI Zhan-ming |
| |
| Affiliation: | CHEN Di,HE Jing-yuan,LI Zhan-ming (College of Electrical , Information Engineering,Lanzhou University of Technology,Lanzhou Gansu 730050,China) |
| |
| Abstract: | Recently, speaker recognition system has already achieved high performance for clean speech, but in noisy environment, the performance of the system may degrade seriously. A method of speaker recognition based on sub-band processing and using phase autocorrelation (PAC) along with its energy as features is proposed. In this method, wideband speech signal is filtered into several sub-bands through Mel filter bank, features of PAC coefficient are extracted by DCT transformation, then feature vectors are model... |
| |
| Keywords: | Sub-band Phase autocorrelation Energy Speaker recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
