Machine translation from signed to spoken languages: State of the art and challenges

M De Coster, D Shterionov, M Van Herreweghe… - Universal Access in the …, 2024 - Springer
Automatic translation from signed to spoken languages is an interdisciplinary research
domain on the intersection of computer vision, machine translation (MT), and linguistics …

Signbert+: Hand-model-aware self-supervised pre-training for sign language understanding

H Hu, W Zhao, W Zhou, H Li - IEEE Transactions on Pattern …, 2023 - ieeexplore.ieee.org
Hand gesture serves as a crucial role during the expression of sign language. Current deep
learning based methods for sign language understanding (SLU) are prone to over-fitting due …

A survey of advancements in real-time sign language translators: integration with IoT technology

M Papatsimouli, P Sarigiannidis, GF Fragulis - Technologies, 2023 - mdpi.com
Real-time sign language translation systems are of paramount importance in enabling
communication for deaf and hard-of-hearing individuals. This population relies on various …

Gloss attention for gloss-free sign language translation

A Yin, T Zhong, L Tang, W **… - Proceedings of the …, 2023 - openaccess.thecvf.com
Most sign language translation (SLT) methods to date require the use of gloss annotations to
provide additional supervision information, however, the acquisition of gloss is not easy. To …

Natural language-assisted sign language recognition

R Zuo, F Wei, B Mak - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Sign languages are visual languages which convey information by signers' handshape,
facial expression, body movement, and so forth. Due to the inherent restriction of …

From rule-based models to deep learning transformers architectures for natural language processing and sign language translation systems: survey, taxonomy and …

N Shahin, L Ismail - Artificial Intelligence Review, 2024 - Springer
With the growing Deaf and Hard of Hearing population worldwide and the persistent
shortage of certified sign language interpreters, there is a pressing need for an efficient …

Transpeech: Speech-to-speech translation with bilateral perturbation

R Huang, J Liu, H Liu, Y Ren, L Zhang, J He… - arxiv preprint arxiv …, 2022 - arxiv.org
Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in
speech representation learning. Specifically, a sequence of discrete representations derived …

Mlslt: Towards multilingual sign language translation

A Yin, Z Zhao, W **, M Zhang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Most of the research to date focuses on bilingual sign language translation (BSLT).
However, such models are inefficient in building multilingual sign language translation …

[PDF][PDF] Contrastive Learning for Sign Language Recognition and Translation.

S Gan, Y Yin, Z Jiang, K **a, L **e, S Lu - IJCAI, 2023 - ijcai.org
There are two problems that widely exist in current end-to-end sign language processing
architecture. One is the CTC spike phenomenon which weakens the visual representational …

SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval

L Jiang, M Wang, Z Li, Y Fang, W Zhou… - Proceedings of the 32nd …, 2024 - dl.acm.org
Different from traditional video retrieval, sign language retrieval is more biased towards
understanding the semantic information of human actions contained in video clips. Previous …