Visual Speech Recognition for Multiple Languages in the Wild
This work addresses the challenge of accurate lip-reading in diverse languages for applications like assistive technology or noisy environments, representing a strong incremental improvement over existing methods.
The paper tackled the problem of visual speech recognition (VSR) across multiple languages by proposing a model with prediction-based auxiliary tasks, hyperparameter optimization, and data augmentations, resulting in outperforming all previous methods on public datasets and even those trained on much larger non-public datasets.
Visual speech recognition (VSR) aims to recognize the content of speech based on lip movements, without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development of much more accurate and robust VSR models than ever before. However, these advances are usually due to the larger training sets rather than the model design. Here we demonstrate that designing better models is equally as important as using larger training sets. We propose the addition of prediction-based auxiliary tasks to a VSR model, and highlight the importance of hyperparameter optimization and appropriate data augmentations. We show that such a model works for different languages and outperforms all previous methods trained on publicly available datasets by a large margin. It even outperforms models that were trained on non-publicly available datasets containing up to to 21 times more data. We show, furthermore, that using additional training data, even in other languages or with automatically generated transcriptions, results in further improvement.