基于状态映射的跨语种自适应研究  

Research on Cross-lingual Adaptation Based on State Mapping

作　　者：夏菽兰[1] 赵力[2] 

机构地区：[1]盐城工学院电气工程学院,江苏盐城224051 [2]东南大学信息科学与工程学院,江苏南京210096

出　　处：《微电子学与计算机》2015年第4期134-137,共4页Microelectronics & Computer

基　　金：国家自然科学基金项目(60472058)

摘　　要：以基于状态映射的中英跨语种自适应方法为研究对象,将状态映射应用于跨语种自适应中,对自适应中两种使用状态映射信息的方式(数据映射和变换映射)进行了比较分析.通过实验发现,基于状态映射的自适应方法具有一定的效果,CSMAPLR算法优于CMLLR算法,而且两种方式各有优劣.The Chinese and English cross-lingual adaptation algorithms are studied,which are based on state mapping method.Two modes of state mapping method applied in cross-lingual adaptation are compared and analyzed.Experiments show that the adaptation algorithms can make sense,and that CSMAPLR is better than CMLLR algorithms.Furthermore,voice quality is better in transform mode than in data mode.And it needs high consistency of speaker characteristics of two original language models.On the contrary,speaker similarity in data mode is better.

关 键 词：状态映射 跨语种自适应 数据映射 变换映射 

分 类 号：TN912.3[电子电信—通信与信息系统]