| 基于修正Mel子带系数的文本无关的说话人识别 |
| |
| 引用本文： | 张庆芳,赵鹤鸣. 基于修正Mel子带系数的文本无关的说话人识别[J]. 计算机工程与应用, 2011, 47(1): 12-14. DOI: 10.3778/j.issn.1002-8331.2011.01.004 |
| |
| 作者姓名： | 张庆芳 赵鹤鸣 |
| |
| 作者单位： | 1.苏州经贸职业技术学院，江苏 苏州 215009 2.苏州大学 电子信息学院，江苏 苏州 215006 |
| |
| 基金项目： | 国家自然科学基金No.61071215~~ |
| |
| 摘 要： | 与文本无关的说话人识别具有用户使用方便、可应用范围较宽等优点，是当前说话人识别技术的研究重点。对文本无关说话人识别系统中的特征参数提取进行了研究，通过对Mel子带系数进行修正，增强了说话人识别系统中说话人之间的频带差异，提高了特征空间中类别的可分性，得到了更能体现说话人个性特征的Mel子带系数，从而提高了说话人识别系统的平均正确识别率。
|
| 关 键 词： | 说话人识别 与文本无关 矢量量化 Mel子带 |
| 收稿时间： | 2010-09-08 |
| 修稿时间： | 2010-11-19 |
Mel frequency subband coefficients based text independent speaker recognition |
| |
| ZHANG Qingfang,ZHAO Heming. Mel frequency subband coefficients based text independent speaker recognition[J]. Computer Engineering and Applications, 2011, 47(1): 12-14. DOI: 10.3778/j.issn.1002-8331.2011.01.004 |
| |
| Authors: | ZHANG Qingfang ZHAO Heming |
| |
| Affiliation: | 1.Suzhou Institute of Trade & Commerce，Suzhou，Jiangsu 215009，China 2.School of Electronics and Information Engineering，Suzhou University，Suzhou，Jiangsu 215006，China |
| |
| Abstract: | Text-independent speaker recognition is an important branch research field of speaker recognition because of its ease-to-use and potential applications in the information technology.This paper focuses on the problems of the feature extraction.Through modifying the Mel frequency subband coefficients,it enhances the differences of the frequency between the people in the system,improves the ability of separating the classes in the feature space.And the parameters can emphasize people's individuality and increa... |
| |
| Keywords: | speaker recognition text independent vector quantization Mel frequency subband |
| 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 |
