SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision

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.

Download the Paper


Written by

Xubo Liu

Egor Lakomkin

Dino Vougioukas

Pingchuan Ma

Honglie Chen

Ruiming Xie

Morrie Doulaty

Niko Moritz

Jachym Kolar

Stavros Petridis

Maja Pantic

Christian Fuegen



Research Topics

Computer Vision

Related Publications

May 06, 2024



Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

Haoyue Tang, Tian Xie

May 06, 2024

April 23, 2024


Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar

Jamie Tolan, Eric Yang, Ben Nosarzewski, Guillaume Couairon, Huy Vo, John Brandt, Justine Spore, Sayantan Majumdar, Daniel Haziza, Janaki Vamaraju, Theo Moutakanni, Piotr Bojanowski, Tracy Johns, Brian White, Tobias Tiecke, Camille Couprie, Edward Saenz

April 23, 2024

April 23, 2024



Generating Illustrated Instructions

Sachit Menon, Ishan Misra, Rohit Girdhar

April 23, 2024

April 18, 2024


Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation

Jonas Kohler, Albert Pumarola, Edgar Schoenfeld, Artsiom Sanakoyeu, Roshan Sumbaly, Peter Vajda, Ali Thabet

April 18, 2024

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.