Towards Practical Lipreading with Distilled and Efficient Models
arXiv:2007.06504
Abstract
Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. However, there is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. In this work, we propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation. Secondly, we propose a series of architectural changes, including a novel Depthwise Separable Temporal Convolutional Network (DS-TCN) head, that slashes the computational cost to a fraction of the (already quite efficient) original model. Thirdly, we show that knowledge distillation is a very effective tool for recovering performance of the lightweight models. This results in a range of models with different accuracy-efficiency trade-offs. However, our most promising lightweight models are on par with the current state-of-the-art while showing a reduction of 8.2x and 3.9x in terms of computational cost and number of parameters, respectively, which we hope will enable the deployment of lipreading models in practical applications.
arXiv commentAccepted to ICASSP 2021
References in corpus (11)
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Decoupled Weight Decay Regularization
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Deep Audio-Visual Speech Recognition
- Label Refinery: Improving ImageNet Classification through Label Progression
- Training Binary Neural Networks with Real-to-Binary Convolutions
- Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students
- Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading
- MobiVSR: A Visual Speech Recognition Solution for Mobile Devices