EMNLP 2023long findings0 citations

Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Methods

Xuan Zhang, Kevin Duh

Abstract

The majority of existing work on sign language recognition encodes signed videos without explicitly acknowledging the phonological attributes of signs. Given that handshape is a vital parameter in sign languages, we explore the potential of handshape-aware sign language recognition. We augment the PHOENIX14T dataset with gloss-level handshape labels, resulting in the new PHOENIX14T-HS dataset. Two unique methods are proposed for handshape-inclusive sign language recognition: a single-encoder network and a dual-encoder network, complemented by a training strategy that simultaneously optimizes both the CTC loss and frame-level cross-entropy loss. The proposed methodology consistently outperforms the baseline performance. The dataset and code can be accessed at: www.anonymous.com.

Sign language recognitionhandshape
BibTeX
@inproceedings{
zhang2023handshapeaware,
title={Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Methods},
author={Xuan Zhang and Kevin Duh},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=qJqJXpysnh}
}
Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Methods · EMNLP 2023