| 基于状态空间模型的子频带语音转换算法 |
| |
| 引用本文： | 徐宁,杨震,张玲华.基于状态空间模型的子频带语音转换算法[J].电子学报,2010,38(3):646-653. |
| |
| 作者姓名： | 徐宁 杨震 张玲华 |
| |
| 作者单位： | 1.南京邮电大学信号处理与传输研究院，江苏南京210003;2.南京邮电大学通信与信息工程学院，江苏南京210003 |
| |
| 基金项目： | 国家863重点项目(No.2006AA010102);;国家自然科学基金(No.608721135,60971129);;江苏省普通高校研究生科研创新计划(No.CX08B_079Z) |
| |
| 摘 要： | 语音转换是一项改变说话人声音特征的技术，该领域主流方法——基于高斯混合模型的全频带参数映射，会导致转换后的语音频谱产生帧间不连续性。本文针对以上问题提出了改进方案：首先引入状态空间模型来模拟语音动态变化特性，其次利用离散小波变换对语音低频和高频部分的参数分为子频带处理。文章最后用主观和客观实验对提出的算法进行的实验仿真和验证。
|
| 关 键 词： | 语音转换 高斯混合模型 状态空间模型 全频带转换 子频带转换 |
| 收稿时间： | 2008-09-24 |
Sub-Band Voice Morphing Algorithm Based on State-Space Model |
| |
| XU Ning,YANG Zhen,ZHANG Ling-hua.Sub-Band Voice Morphing Algorithm Based on State-Space Model[J].Acta Electronica Sinica,2010,38(3):646-653. |
| |
| Authors: | XU Ning YANG Zhen ZHANG Ling-hua |
| |
| Affiliation: | 1. Institute of Signal Processing and Transmission of Nanjing University of Posts and Telecommunications，Nanjing，Jiangsu 210003，China;2. College of Telecommunication & Information Engineering of Nanjing University of Posts and Telecommunications，Nanjing，Jiangsu 10003，China |
| |
| Abstract: | Voice morphing is a technique to modify a source speaker's speech to sound as if it was spoken by solne desig-nated target speaker.The Gaussian mixture model(GMM)based transformations combined with full-band extracted feature paranle-ters have been commonly studied.However.these methods often introduce problems such as artifacts and discontinuities.In order to resolve the problem mentioned above,state-space model(SSM)iS first used to describe the relationship between the source speech and the target speech ... |
| |
| Keywords: | voice morphing Gaussian mixture model state-space model full-band conversion sub-band conversion |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
