Harnessing GANs for Zero-shot Learning of New Classes in Visual Speech Recognition
This addresses the data scarcity issue in VSR for applications like assistive technologies, though it is incremental as it applies an existing GAN method to a new domain.
The paper tackles the problem of low accuracy in Visual Speech Recognition (VSR) due to scarce training data for unseen classes by using GANs to generate new class samples, resulting in a 27% increase in accuracy and enabling speaker-independent out-of-vocabulary phrase handling.
Visual Speech Recognition (VSR) is the process of recognizing or interpreting speech by watching the lip movements of the speaker. Recent machine learning based approaches model VSR as a classification problem; however, the scarcity of training data leads to error-prone systems with very low accuracies in predicting unseen classes. To solve this problem, we present a novel approach to zero-shot learning by generating new classes using Generative Adversarial Networks (GANs), and show how the addition of unseen class samples increases the accuracy of a VSR system by a significant margin of 27% and allows it to handle speaker-independent out-of-vocabulary phrases. We also show that our models are language agnostic and therefore capable of seamlessly generating, using English training data, videos for a new language (Hindi). To the best of our knowledge, this is the first work to show empirical evidence of the use of GANs for generating training samples of unseen classes in the domain of VSR, hence facilitating zero-shot learning. We make the added videos for new classes publicly available along with our code.