SparseVSR: Lightweight and Noise Robust Visual Speech Recognition
share
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 outperform the dense equivalent up to 70 model on 7 different visual noise types and achieve an overall absolute improvement of more than 2 confirm that sparse networks are more resistant to noise than dense networks.
READ FULL TEXT