计算机的研究与发展ISSN.pdfVIP

计算机研究与发展 ISSN N 111777TP Journal of Computer Research and Development 43 ( 1) : 145～152 , 2006 文本- 视觉语音合成综述 1 ,2 2 王志明 　　陶建华 1 (北京科技大学计算机科学与技术系 　北京 　100083) 2 ( 中国科学院自动化研究所模式识别国家重点实验室 　北京 　100080) (wangzhiming @tsinghuaorgcn) A Revie w of TexttoVisual Speech Synthesis Wang Zhiming1 ,2 and Tao Jianhua2 1 ( ) Depart ment of Computer Science and Technology , Beijin g U niversity of Science and Technology , Beijin g 100083 2 ( ) N ational L aboratory of Pattern Recognition , Institute of A utom ation , Chinese Academy of Sciences , Beijin g 100080 Abstract 　Visual information is important to the understanding of speech Not only hearingimpaired peo ple , but people with normal hearing also make use of visual information that accompanies speech , especially when the acoustic speech is degraded in the noise environment As texttospeech ( TTS) synthesis makes computer speak like human , texttovisual speech ( TTVS) synthesis by computer face animation can incor porate bimodalit y of speech into humancomputer interaction interface in order to make it friendly The stateoftheart of texttovisual speech synthesis research is reviewed Two classes of approaches , parame ter control approach and data driven approach , are developed in visual speech synthesis For the parameter control approach , three key problems are discussed : face model construction , animation control parameters definition , and the dynamic properties of control parameters For the data driven approach , three ma