1. 中国传媒大学信息与通信工程学院,北京 100024
2. 北京化工大学,北京 100089
3. 北京理工大学信息与电子学院,北京 100081
[ "靳聪(1986- ),女,博士,中国传媒大学信息与通信工程学院副教授,主要研究方向为强化学习、音乐人工智能和音频信号处理" ]
[ "王洁(2001- ),女,中国传媒大学信息与通信工程学院硕士生,主要研究方向为深度合成和智能音视频处理" ]
[ "郭子淳(1987- ),男,博士,北京化工大学副教授,主要研究方向为未来影像与具身交互叙事" ]
[ "王晶(1980- ),女,博士,北京理工大学信息与电子学院副教授,主要研究方向为语音与音频信号处理、多媒体通信和虚拟现实" ]
修回:2023-08-01,
网络首发:2023-09,
纸质出版:2023-09-15
移动端阅览
靳聪, 王洁, 郭子淳, 等. 融合音画同步的唇形合成研究[J]. 智能科学与技术学报, 2023,5(3):397-405.
Cong JIN, Jie WANG, Zichun GUO, et al. Lipsynthesis incorporating audio-visual synchronisation[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(3): 397-405.
靳聪, 王洁, 郭子淳, 等. 融合音画同步的唇形合成研究[J]. 智能科学与技术学报, 2023,5(3):397-405. DOI: 10.11959/j.issn.2096-6652.202335.
Cong JIN, Jie WANG, Zichun GUO, et al. Lipsynthesis incorporating audio-visual synchronisation[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(3): 397-405. DOI: 10.11959/j.issn.2096-6652.202335.
以视频为载体的信息传播方式兴盛发展,视频的音画同步逐渐成为衡量视频质量的重要标准。深度合成技术在国际传播领域不断进入大众视野,融合音画同步的唇形合成技术吸引了越来越多的关注。现有唇形合成模型主要是基于静态图像的唇形合成,对于动态视频的合成效果不佳,且大多采用英文数据集进行训练,导致中文普通话合成效果较差。针对这些问题,基于对Wav2Lip唇形合成模型的研究,对其进行中文语境下的优化实验,通过多组实验测试了不同路线的训练模型效果,为后续Wav2Lip系列研究提供重要的参考价值。实现由语音驱动到文字驱动的唇形合成,并对唇形合成在虚拟数字人等多领域的应用展开讨论,为唇形合成技术更广阔的应用与发展奠定基础。
With the flourishing development of video-based information dissemination
audio and video synchronization is gradually becoming an important standard for measuring video quality.Deep synthesis technology has been entering the public's view in the international communication field
and lip-sync technology integrating audio and video synchronization has attracted more and more attention.The existing lip-synthesis models are mainly based on lip-synthesis of static images
which are not effective for synthesis of dynamic videos
and most of them use English datasets for training which results in poor synthesis of Chinese Mandarin.To address these problems
this paper conducted optimization experiments on the Wav2Lip lip synthesis model in Chinese context based on its research foundation
and tested the effect of different routes of training models through multiple sets of experiments
which provided important reference values for the subsequent Wav2Lip series research.This study realized lip synthesis from speech-driven to text-driven
discussed the application of lip synthesis in multiple fields such as virtual digital human
and laid the foundation for the broader application and development of lip synthesis technology.
PRAJWAL K R , MUKHOPADHYAY R , NAMBOODIRI V P , et al . A lip sync expert is all you need for speech to lip generation in the wild [C ] // Proceedings of the 28th ACM International Conference on Multimedia . New York:ACM , 2020 : 484 - 492 .
CHUNG J S , JAMALUDIN A , ZISSERMAN A , et al . You said that? [EB ] . arXiv preprint , 2017 ,arXiv:1705.02966.
KARPATHY A , TODERICI G , SHETTY S , et al . Large-scale video classification with convolutional neural networks [C ] // Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2014 : 1725 - 1732 .
SUWAJANAKORN S , SEITZ S M , KEMELMACHER-SHLIZERMAN I . Synthesizing Obama:learning lip sync from audio [J ] . ACM Transactions on Graphics , 2017 , 36 ( 4 ): 1 - 13 .
CHEN L L , LI Z H , MADDOX R K , et al . Lip movements generation at a glance [C ] // Proceedings of European Conference on Computer Vision . Cham:Springer , 2018 : 538 - 553 .
PRAJWAL K R , MUKHOPADHYAY R , PHILIP J , et al . Towards automatic face-to-face translation [C ] // Proceedings of the 27th ACM International Conference on Multimedia . New York:ACM , 2019 : 1428 - 1436 .
CHUNG J S , ZISSERMAN A . Out of time:automated lip sync in the wild [C ] // Proceedings of Computer Vision-ACCV 2016 Workshops . Cham:Springer , 2017 : 251 - 263 .
TOMAR S . Converting video formats with FFmpeg [J ] . Linux Journal , 2006 ( 146 ): 10 .
MCFEE B , RAFFEL C , LIANG D , et al . Librosa:audio and music signal analysis in python [C ] // Proceedings of the 14th Python in Science Conference .[S.l:s.n. ] , 2015 : 18 - 25 .
CRESWELL A , WHITE T , DUMOULIN V , et al . Generative adversarial networks:an overview [J ] . IEEE Signal Processing Magazine , 2018 , 35 ( 1 ): 53 - 65 .
0
浏览量
620
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
