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.

深度学习神经网络在视觉语音识别方面取得了前所未有的成功，本研究通过不同的基于幅度的修剪技术，生成了一个轻量级模型，其在视觉噪声存在的情况下表现出比其密集模型等效性能更高的水平，在 LRS3 数据集的 10％稀疏度下实现了最先进的结果，并在 70％稀疏度下优于密集等效性水平，我们在 7 种不同的视觉噪声类型上评估了我们的 50％稀疏模型，并且相对于密集等效性模型，绝对词错误率的改善超过 2％，我们的结果证实稀疏网络比密集网络对噪声更具抗干扰性。