Given a face image and a speech audio, talking face generation refers to synthesizing a face video speaking the given speech.It has wide applications in movie dubbing, teleconference, virtual assistant, etc.This paper gives an overview of research progress on talking face generation in recent years.The author first reviews traditional talking face generation methods.Then, deep learning talking face generation methods, including talking face synthesis for a specific identity and talking face synthesis for an arbitrary identity, are summarized.The author then surveys recent detail-aware talking face generation methods, including noise based approaches, eye conversion based approaches, and facial anatomy based approaches.Next, the author surveys the talking head generation methods, such as video/image driven talking head generation, pose information-driven talking head generation, and audio-driven talking head generation.Finally, some future directions for talking face generation are highlighted.

Shiguang Liu

Journal of the Audio Engineering Society

THE JOURNAL OF THE AUDIO ENGINEERING SOCIETY（AES 的官方出版物）是唯一专门针对音频技术的同行评审期刊。每年出版 10 次，面向所有 AES 成员和订阅者。期刊包含最先进的技术论文和工程报告；涵盖及时主题的专题文章； AES公约和其他社会活动的前后报告；来自世界各地 AES 部门的新闻；标准和教育委员会的工作；音频领域的会员新闻、专利、新产品和具有新闻价值的发展。

The AES: Journal of the Audio Engineering Society is the official publication of the Audio Engineering Society (AES) and the only peer-reviewed journal dedicated to audio technology. Published ten times a year, it is available to all AES members and subscribers. The journal features cutting-edge technical papers and engineering reports, topical articles on timely subjects, and reports on AES conventions and other society activities. It also includes news from AES sections around the world, updates from the Standards and Education Committee, and member news, patents, new products, and other noteworthy developments in the audio field.

《AES: Journal of the Audio Engineering Society》是音频工程学会（AES）的官方期刊，也是唯一专注于音频技术的同行评审期刊。该期刊每年出版10期，面向所有AES成员和订阅者。期刊内容包括前沿的技术论文和工程报告，涵盖当前热点话题的专题文章，以及AES公约和其他社会活动的前后报告。此外，期刊还提供来自全球AES分会的新闻、标准和教育委员会的工作动态，以及音频领域的会员新闻、专利、新产品和其他具有新闻价值的发展。

Category	Quartile
工程技术	4
工程技术, 声学	4
工程技术, 工程综合	4

Audio-Driven Talking Face Generation: A Review

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
ENGINEERING, MULTIDISCIPLINARY	3