Tout DSpace

Parcourir par sujet "Visual speech recognition"

Voici les éléments 1-2 de 2

    • Exploring ROI size in deep learning based lipreading 

      Koumparoulis A., Potamianos G., Mroueh Y., Rennie S.J. (2017)
      Automatic speechreading systems have increasingly exploited deep learning advances, resulting in dramatic gains over traditional methods. State-of-the-art systems typically employ convolutional neural networks (CNNs), ...

    • Resource-adaptive deep learning for visual speech recognition 

      Koumparoulis A., Potamianos G., Thomas S., da Silva Morais E. (2020)
      We focus on the problem of efficient architectures for lipreading that allow trading-off computational resources for visual speech recognition accuracy. In particular, we make two contributions: First, we introduce ...