English

AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model

Computer Vision and Pattern Recognition 2024-01-15 v2 Multimedia Audio and Speech Processing Image and Video Processing

Abstract

Visual Speech Recognition (VSR) is the task of predicting spoken words from silent lip movements. VSR is regarded as a challenging task because of the insufficient information on lip movements. In this paper, we propose an Audio Knowledge empowered Visual Speech Recognition framework (AKVSR) to complement the insufficient speech information of visual modality by using audio modality. Different from the previous methods, the proposed AKVSR 1) utilizes rich audio knowledge encoded by a large-scale pretrained audio model, 2) saves the linguistic information of audio knowledge in compact audio memory by discarding the non-linguistic information from the audio through quantization, and 3) includes Audio Bridging Module which can find the best-matched audio features from the compact audio memory, which makes our training possible without audio inputs, once after the compact audio memory is composed. We validate the effectiveness of the proposed method through extensive experiments, and achieve new state-of-the-art performances on the widely-used LRS3 dataset.

Keywords

Cite

@article{arxiv.2308.07593,
  title  = {AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model},
  author = {Jeong Hun Yeo and Minsu Kim and Jeongsoo Choi and Dae Hoe Kim and Yong Man Ro},
  journal= {arXiv preprint arXiv:2308.07593},
  year   = {2024}
}

Comments

Accepted by IEEE Transactions on Multimedia

R2 v1 2026-06-28T11:55:48.204Z