基于语音信号的发音器官运动估计方法综述  

A Survey of Articulatory Estimation Methods Based on Speech Signal

作　　者：汪洋[1] 李绍彬[1] 边洁蕊 WANG Yang;LI Shao-bin;BIAN Jie-rui(Information Engineering School,Communication University of China,Beijing 100024,China)

机构地区：[1]中国传媒大学信息工程学院,北京100024

出　　处：《中国传媒大学学报（自然科学版）》2018年第1期57-62,共6页Journal of Communication University of China：Science and Technology

摘　　要：基于语音信号的发音器官运动估计,是根据说话人语音推断发音器官运动过程的技术,在语言学、医学、影视动画学等领域有广阔应用前景。本文主要对基于单元选择模型和回归模型实现该技术的方法进行介绍。单元选择模型法部分阐述了码本库建设、语音单元切分、选择算法设计、拼接合成算法等方面的研究现状。回归模型法部分阐述了此类问题中隐马尔科夫模型、高斯混合模型、人工神经网络等回归算法的研究现状。最后,文章进行了总结和展望。Articulatory estimation methods based on speech signal is a technology of inferring the speech organs’movement process according to the speakers'voice,and has broad application prospects in the fields of linguistics,medicine,film animation and so on.This paper mainly introduces the unit selection model method and the regression model method.Firstly,the unit selection model to realize this technology is introduced.The research status of codebook library construction,speech unit segmentation,selection algorithm design and stitching synthesis algorithm are introduced.Secondly,the regression model to realize this technology is introduced.The research status of regression algorithms in this problem,such as hidden Markov model,Gaussian mixture model,artificial neural network and so on,are expounded.Finally,the paper summarizes the two methods and gives the prospect.

关 键 词：语音反转 单元选择模型 码本模型 回归模型 

分 类 号：TN912[电子电信—通信与信息系统]