HRI-JP HOME > Research > Publications > Augmenting Sparse Corpora for Enhanced Sign Language Recognition and Generation



Advanced Search

May 2018

Augmenting Sparse Corpora for Enhanced Sign Language Recognition and Generation

  • H. Brock, J. Rengot, K. Nakadai,
  • in Proceedings of the LREC 2018 Workshop “8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community”,
  • LREC 2018 Sign Language Workshop Programme Committee,
  • 2018,
  • pp. 15-22,
  • Conference paper

The collection of signed utterances for recognition and generation of Sign Language (SL) is a costly and labor-intensive task. As a result, SL corpora are usually considerably smaller than their spoken language or image data counterparts. This is problematic, since the accuracy and applicability of a neural network depends largely on the quality and amount of its underlying training data. Common data augmentation strategies to increase the number of available training data are usually not applicable to the spatially and temporally constrained motion sequences of a SL corpus. In this paper, we therefore discuss possible data manipulation methods on the base of a collection of motion-captured SL sentence expressions. Evaluation of differently trained network architectures shows a significant reduction of overfitting by inclusion of the augmented data. Simultaneously, the accuracy of both sign recognition and generation was improved, indicating that the proposed data augmentation methods are beneficial for constrained and sparse data sets.

Search by Other Conditions

Entry type