Out of Time: Automated Lip Sync in the Wild

被引:217
|
作者
Chung, Joon Son [1 ]
Zisserman, Andrew [1 ]
机构
[1] Univ Oxford, Visual Geometry Grp, Dept Engn Sci, Oxford, England
基金
英国工程与自然科学研究理事会;
关键词
SPEECH; SYNCHRONIZATION; TRANSLATION;
D O I
10.1007/978-3-319-54427-4_19
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The goal of this work is to determine the audio-video synchronisation between mouth motion and speech in a video. We propose a two-stream ConvNet architecture that enables the mapping between the sound and the mouth images to be trained end-to-end from unlabelled data. The trained network is used to determine the lip-sync error in a video. We apply the network to two further tasks: active speaker detection and lip reading. On both tasks we set a new state-of-the-art on standard benchmark datasets.
引用
收藏
页码:251 / 263
页数:13
相关论文
共 50 条
  • [41] Out of sync, out of society: Political beliefs and social networks
    Joo, Won-tak
    Fletcher, Jason
    NETWORK SCIENCE, 2020, 8 (03) : 445 - 468
  • [42] Out of sight, out of sync: Understanding conflict in distributed teams
    Hinds, PJ
    Bailey, DE
    ORGANIZATION SCIENCE, 2003, 14 (06) : 615 - 632
  • [43] Interpolation of packet loss and lip sync error on IP media
    Mued, L
    Lines, B
    Furnell, S
    CCCT 2003, VOL 5, PROCEEDINGS: COMPUTER, COMMUNICATION AND CONTROL TECHNOLOGIES: II, 2003, : 249 - 253
  • [44] WILD MAMMALS BILL RUNS OUT OF TIME
    不详
    VETERINARY RECORD, 1995, 137 (21) : 527 - 528
  • [45] Evaluation of a Korean Lip-Sync System for an Android Robot
    Hyung, Hyun-Jun
    Ahn, Byeong-Kyu
    Choi, Dongwoon
    Lee, Dukyeon
    Lee, Dong-Wook
    2016 13TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS AND AMBIENT INTELLIGENCE (URAI), 2016, : 78 - 82
  • [46] Animating Lip-Sync Characters With Dominated Animeme Models
    Chen, Yu-Mei
    Huang, Fu-Chun
    Guan, Shuen-Huei
    Chen, Bing-Yu
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2012, 22 (09) : 1344 - 1353
  • [47] Lip Reading in the Wild
    Chung, Joon Son
    Zisserman, Andrew
    COMPUTER VISION - ACCV 2016, PT II, 2017, 10112 : 87 - 103
  • [48] DTV lip-sync test using time indexed audio and video signals without effect on program
    Han, CH
    Kim, ES
    Jang, SW
    Sohng, KI
    ICCE: 2003 INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, DIGEST OF TECHNICAL PAPERS, 2003, : 194 - 195
  • [49] Heterogeneous Sensor Fusion With Out Of Sync Data
    Chen, Biao
    Varshney, Pramod K.
    Zulch, Peter
    Distasio, Marcello
    Niu, Ruixin
    Shen, Dan
    Lu, Jingyang
    Chen, Genshe
    2020 IEEE AEROSPACE CONFERENCE (AEROCONF 2020), 2020,
  • [50] Out of sync: antimicrobial drug development for children
    LANCET CHILD & ADOLESCENT HEALTH, 2024, 8 (08): : 629 - 629