April 20, 2023
Recently reported state-of-the-art results in visual speech recognition (VSR) often rely on increasingly large amounts of video data, while the publicly available transcribed video datasets are limited in size. In this paper, for the first time, we study the potential of leveraging synthetic visual data for VSR. Our method, termed SynthVSR, substantially improves the performance of VSR systems with synthetic lip movements. The key idea behind SynthVSR is to leverage a speech-driven lip animation model that generates lip movements conditioned on the input speech. The speech-driven lip animation model is trained on an unlabeled audio-visual dataset and could be further optimized towards a pre-trained VSR model when labeled videos are available. As plenty of transcribed acoustic data and face images are available, we are able to generate large-scale synthetic data using the proposed lip animation model for semi-supervised VSR training. We evaluate the performance of our approach on the largest public VSR benchmark - Lip Reading Sentences 3 (LRS3). SynthVSR achieves a WER of 43.3% with only 30 hours of real labeled data, outperforming off-the-shelf approaches using thousands of hours of video. The WER is further reduced to 27.9% when using all 438 hours of labeled data from LRS3, which is on par with the state-of-the-art self-supervised AV-HuBERT method. Furthermore, when combined with large-scale pseudo-labeled audio-visual data SynthVSR yields a new state-of-the-art VSR WER of 16.9% using publicly available data only, surpassing the recent state-of-the-art approaches trained with 29 times more non-public machine-transcribed video data (90,000 hours). Finally, we perform extensive ablation studies to understand the effect of each component in our proposed method.
Written by
Xubo Liu
Egor Lakomkin
Dino Vougioukas
Pingchuan Ma
Honglie Chen
Ruiming Xie
Morrie Doulaty
Niko Moritz
Jachym Kolar
Stavros Petridis
Publisher
CVPR
Research Topics
April 17, 2025
Daniel Bolya, Po-Yao Huang, Peize Sun, Jang Hyun Cho, Andrea Madotto, Chen Wei, Tengyu Ma, Jiale Zhi, Jathushan Rajasegaran, Hanoona Rasheed, Junke Wang, Marco Monteiro, Hu Xu, Shiyu Dong, Nikhila Ravi, Daniel Li (FAIR), Piotr Dollar, Christoph Feichtenhofer
April 17, 2025
April 17, 2025
Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi, Triantafyllos Afouras, Tushar Nagarajan, Muhammad Maaz, Yale Song, Tengyu Ma, Shuming Hu, Hanoona Rasheed, Peize Sun, Po-Yao Huang, Daniel Bolya, Suyog Jain, Miguel Martin, Huiyu Wang, Nikhila Ravi, Shashank Jain, Tammy Stark, Shane Moon, Babak Damavandi, Vivian Lee, Andrew Westbury, Salman Khan, Philipp Krähenbühl, Piotr Dollar, Lorenzo Torresani, Kristen Grauman, Christoph Feichtenhofer
April 17, 2025
April 14, 2025
Yeongmin Kim, Sotiris Anagnostidis, Yuming Du, Edgar Schoenfeld, Jonas Kohler, Markos Georgopoulos, Albert Pumarola, Ali Thabet, Artsiom Sanakoyeu
April 14, 2025
March 30, 2025
Guy Yariv, Yuval Kirstain, Amit Zohar, Shelly Sheynin, Yaniv Taigman, Yossef (Yossi) Adi, Sagie Benaim, Adam Polyak
March 30, 2025
Our approach
Latest news
Foundational models