| 基于混合线性变换的语声转换算法 |
| |
| 引用本文： | 简志华, 杨震. 基于混合线性变换的语声转换算法[J]. 电子与信息学报, 2007, 29(7): 1700-1702. doi: 10.3724/SP.J.1146.2006.00787 |
| |
| 作者姓名： | 简志华 杨震 |
| |
| 作者单位： | 南京邮电大学信号与信息处理研究所,南京,210003;南京邮电大学信号与信息处理研究所,南京,210003 |
| |
| 基金项目： | 江苏省教育厅青蓝工程项目 |
| |
| 摘 要： | 针对在没有对称语音库的情况下，该文提出了一种基于混合线性变换的语声转换算法，在最大似然估计准则下，使用EM迭代算法计算变换函数的参量。为了减小线性加权对语音谱包络的平滑作用，使用线性调频Z变换来调节语音信号的LPC系数。客观评测和主观感受的实验结果都表明，基于混合线性变换的语声转换算法也可以取得与传统语声转换技术相当的转换效果，解除了传统语声转换技术需要对称语音库的要求。
|
| 关 键 词： | 语声转换 混合线性变换 最大期望算法 线性调频Z变换 |
| 文章编号： | 1009-5896（2007）07-1700-03 |
| 收稿时间： | 2006-06-06 |
| 修稿时间： | 2006-06-062006-10-30 |
An Algorithm for Voice Conversion Based on Mixtures of Linear Transformation |
| |
| Jian Zhi-hua, Yang Zhen. An Algorithm for Voice Conversion Based on Mixtures of Linear Transformation[J]. Journal of Electronics & Information Technology, 2007, 29(7): 1700-1702. doi: 10.3724/SP.J.1146.2006.00787 |
| |
| Authors: | Jian Zhi-hua Yang Zhen |
| |
| Affiliation: | Institute of Signal and Information Processing, Nanjing Univ. of Post and Telecom.,Nanjing 210003, China |
| |
| Abstract: | This paper proposes an algorithm for voice conversion based on mixtures of linear transformation which avoids the need for parallel training corpus inherent in conventional approaches. In maximum likelihood framework the EM algorithm is used to compute the parameters of the transfer function. And the chirp Z-transform is utilized to enhance the smoothed spectral envelop due to the linear weighted averaging. The proposed voice conversion system is evaluated using both objective and subjective measures. The experiment results demonstrate that the proposed approach is capable of effectively transforming speaker identity and can achieve comparable results of the conventional methods where a parallel corpus is needed. |
| |
| Keywords: | Voice conversion Ms-LT EM algorithm Chirp Z-transform |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子与信息学报》浏览原始摘要信息 |
|
点击此处可从《电子与信息学报》下载全文 |
