基于话者无关模型的说话人转换方法 - 模式识别与人工智能.pdf

第26 卷摇 第 3 期摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 模式识别与人工智能摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 Vol.26摇 No.3 摇 2013年3月摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 PR AI摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 Mar摇 摇 2013 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 摇 基于话者无关模型的说话人转换方法* 陈凌辉摇 摇 凌震华摇 摇 戴礼荣 (中国科学技术大学 语音及语言信息处理国家工程实验室摇 合肥230027) 摘摇 要摇 提出一种基于话者无关模型的说话人转换方法.考虑到音素信息共同存在于所有说话人的语音中,假设 存在一个可以用高斯混合模型来描述的话者无关空间,且可用分段线性变换来描述该空间到各说话人相关空间之 间的映射关系.在一个多说话人的数据库上,用话者自适应训练算法来训练模型,并在转换阶段使用源目标说话人 空间到话者无关空间的变换关系来构造源与目标之间的特征变换关系,快速、灵活的构造说话人转换系统.通过主 观测听实验来验证该算法相对于传统的基于话者相关模型方法的优点. 关键词摇 说话人转换,话者无关模型,高斯混合模型,话者自适应训练 中图法分类号摇 TN912.33 Voice Conversion Based on Speaker Independent Model CHEN Ling鄄Hui,LINGZhen鄄Hua,DAI Li鄄Rong (National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei230027) ABSTRACT A voice conversion method based on speaker independent (SI) model is proposed. Considering the phoneme information that commonly exists in every speakers speech,an SI space described only by the phoneme information is assumed to exist. Gaussian mixture model (GMM) is adopted to model the distribution of the SI space,and the mapping relations from speaker dependent (SD) space to SI space are described by linear transformations. The SI model is trained by using speaker adaptive training (SAT) algorithm on a multi鄄speaker database. In the conversion phase,the conversion function from source space to target space is quickly andflexibly built byjoining the transformationsfrom source space to SI spaceandSIspacetotargetspace. Theadvantageoftheproposedmethodisprovedbytheresultsof some listening tests compared with two representat