English

SparseVSR: Lightweight and Noise Robust Visual Speech Recognition

Computer Vision and Pattern Recognition 2023-07-11 v1

Abstract

Recent advances in deep neural networks have achieved unprecedented success in visual speech recognition. However, there remains substantial disparity between current methods and their deployment in resource-constrained devices. In this work, we explore different magnitude-based pruning techniques to generate a lightweight model that achieves higher performance than its dense model equivalent, especially under the presence of visual noise. Our sparse models achieve state-of-the-art results at 10% sparsity on the LRS3 dataset and outperform the dense equivalent up to 70% sparsity. We evaluate our 50% sparse model on 7 different visual noise types and achieve an overall absolute improvement of more than 2% WER compared to the dense equivalent. Our results confirm that sparse networks are more resistant to noise than dense networks.

Keywords

Cite

@article{arxiv.2307.04552,
  title  = {SparseVSR: Lightweight and Noise Robust Visual Speech Recognition},
  author = {Adriana Fernandez-Lopez and Honglie Chen and Pingchuan Ma and Alexandros Haliassos and Stavros Petridis and Maja Pantic},
  journal= {arXiv preprint arXiv:2307.04552},
  year   = {2023}
}

Comments

Accepted to Interspeech 2023

R2 v1 2026-06-28T11:25:57.563Z