深度视觉语音生成研究进展与展望
2024,46(2):123-138
刘丽
国防科技大学 电子科学学院, 湖南 长沙 410073，lilyliu_nudt@163.com
隋金坪
海军大连舰艇学院 作战软件与仿真研究所, 辽宁 大连 116016
丁丁
国防科技大学 教研保障中心, 湖南 长沙 410073
赵凌君
国防科技大学 电子科学学院, 湖南 长沙 410073
匡纲要
国防科技大学 电子科学学院, 湖南 长沙 410073
盛常冲
海军工程大学 电磁能技术全国重点实验室, 湖北 武汉 430033，shengcc_nudt@163.com
国防科技大学 电子科学学院, 湖南 长沙 410073，lilyliu_nudt@163.com
隋金坪
海军大连舰艇学院 作战软件与仿真研究所, 辽宁 大连 116016
丁丁
国防科技大学 教研保障中心, 湖南 长沙 410073
赵凌君
国防科技大学 电子科学学院, 湖南 长沙 410073
匡纲要
国防科技大学 电子科学学院, 湖南 长沙 410073
盛常冲
海军工程大学 电磁能技术全国重点实验室, 湖北 武汉 430033，shengcc_nudt@163.com
摘要：
为了进一步推进深度学习技术驱动的视觉语音生成相关科学问题的研究进展,阐述了视觉语音生成的研究意义与基本定义,并深入剖析了该领域面临的难点与挑战；在此基础上,介绍了目前视觉语音生成研究的现状与发展水平,基于生成框架的区别对近期主流方法进行了梳理、归类和评述；最后探讨视觉语音生成研究潜在的问题和可能的研究方向。
为了进一步推进深度学习技术驱动的视觉语音生成相关科学问题的研究进展,阐述了视觉语音生成的研究意义与基本定义,并深入剖析了该领域面临的难点与挑战；在此基础上,介绍了目前视觉语音生成研究的现状与发展水平,基于生成框架的区别对近期主流方法进行了梳理、归类和评述；最后探讨视觉语音生成研究潜在的问题和可能的研究方向。
基金项目：
国家自然科学基金资助项目(61872379)
国家自然科学基金资助项目(61872379)
Reasearch progress and prospects of deep learning for visual speech generation
LIU Li
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China,lilyliu_nudt@163.com
SUI Jinping
Operational Software and Simulation Institute, Dalian Navy Academy, Dalian 116016, China
DING Ding
Center for Teaching and Research Support, National University of Defense Technology, Changsha 410073, China
ZHAO Lingjun
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
KUANG Gangyao
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
SHENG Changchong
National Key Laboratory of Electromagnetic Energy, Naval University of Engineering, Wuhan 430033, China,shengcc_nudt@163.com
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China,lilyliu_nudt@163.com
SUI Jinping
Operational Software and Simulation Institute, Dalian Navy Academy, Dalian 116016, China
DING Ding
Center for Teaching and Research Support, National University of Defense Technology, Changsha 410073, China
ZHAO Lingjun
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
KUANG Gangyao
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
SHENG Changchong
National Key Laboratory of Electromagnetic Energy, Naval University of Engineering, Wuhan 430033, China,shengcc_nudt@163.com
Abstract：
In order to further advance the development of visual speech learning, the task definition and research significance of visual speech generation was expounded and the difficulties and challenges were deeply analyzed in this field. Besides, the current status and development level of visual speech generation research was introduced, and the recent mainstream methods were sorted, classified and commented based on the difference of generation frameworks. At the end of the paper, the potential problems and possible research directions of visual speech generation were discussed.
In order to further advance the development of visual speech learning, the task definition and research significance of visual speech generation was expounded and the difficulties and challenges were deeply analyzed in this field. Besides, the current status and development level of visual speech generation research was introduced, and the recent mainstream methods were sorted, classified and commented based on the difference of generation frameworks. At the end of the paper, the potential problems and possible research directions of visual speech generation were discussed.
收稿日期：
2022-06-09
2022-06-09
