基于混合映射模型的语音转换算法研究  

A hybrid method to convert acoustic features for voice conversion

作　　者：康永国[1] 双志伟 陶建华[1] 张维 

机构地区：[1]中国科学院自动化研究所,北京100080 [2]IBM中国研究中心,北京100094

出　　处：《声学学报》2006年第6期555-562,共8页Acta Acustica

基　　金：国家自然科学基金资助项目(60575032)

摘　　要：分析了语音转换研究中使用高斯混合模型映射算法时转换特征出现过平滑的问题,认为协方差矩阵估计不准确导致的转换特征细节信息的丢失是产生过平滑问题的主要原因,提出了使用码本映射和高斯混合模型共同转换声学特征细节的混合映射算法。此外提出了利用音素信息进行快速高斯混合模型训练的训练方法。客观评价表明使用音素信息的训练方法比常规方法性能指标平均提高了12．87％,而混合映射算法在使用音素信息的训练方法基础上比传统高斯混合模型转换算法性能指标提高了27．13％The overly smoothing problem of GMM mapping method is first analyzed, and lost spectral details arising from improper covariance matrixes are considered as the main causation. Thus a hybrid mapping method, which converts envelope-subtracted spectral details by GMM and phone-tied codebook mapping method, is proposed. GMM training in this paper is performed in each phonetic data for faster GMM training. Objective evaluations based on performance indices show that the performance of proposed training method with phonetic information averagely improves 12.87% with tradition GMM training method, and proposed mapping method can improve 27.13% with optimal parameters comparing traditional GMM mapping algorithm with new training method.

关 键 词：高斯混合模型 转换算法 映射模型 语音转换 映射算法 训练方法 转换特征 性能指标 

分 类 号：TN912.3[电子电信—通信与信息系统]