Challenge: Existing research on automatic Sign Language Processing (SLP) has focused on recognizing lexical signs, but other gestural units like iconic structures need to be recognized.
Approach: They propose a public remake of the French Sign Language part of the Dicta-Sign corpus with clean annotations and a Convolutional-Recurrent Neural Network to train and test it.
Outcome: The proposed version of the publicly available SL corpus Dicta-Sign is limited to its French Sign Language part and includes lexical and non-lexical annotations over 11 hours of video recording with 35000 manual units.

Similar Papers

A Low-Cost Motion Capture Corpus in French Sign Language for Interpreting Iconicity and Spatial Referencing Mechanisms (2022.lrec-1)

Copied to clipboard

Challenge: Existing tools for automatic translation of sign language videos into transcribed texts are limited.
Approach: They propose to use deep learning methods to circumvent the use of models in spatial referencing recognition by a 3D skeleton and a software program to capture and post-process the LSF-SHELVES corpus.
Outcome: The proposed system targets iconicity and spatial referencing in french sign language . it is light-weight and low-cost to collect data from a large panel of signers .
Rosetta-LSF: an Aligned Corpus of French Sign Language and French for Text-to-Sign Translation (2022.lrec-1)

Copied to clipboard

Challenge: a new corpus of french Sign Language (LSF) data is created to support future studies on the automatic translation of written French into LSF, rendered through the animation of a virtual signer.
Approach: They propose to use a French Sign Language corpus called "Rosetta-LSF" it is intended to support studies on automatic translation of written French into LSF .
Outcome: The proposed corpus supports future studies on automatic translation of written French into LSF, rendered through animation of a virtual signer.
LSF-ANIMAL: A Motion Capture Corpus in French Sign Language Designed for the Animation of Signing Avatars (2020.lrec-1)

Copied to clipboard

Challenge: Signing avatars are often procedurally animated, resulting in robotic and unnatural movements, which are therefore rejected by the Deaf community.
Approach: They propose to use a French Sign Language corpus to create an avatar that can be edited from motion capture data to create new signs and utterances.
Outcome: The proposed corpus is based on a french Sign Language (LSF) corpus composed of captured signs and sentences.
Modeling French Sign Language: a proposal for a semantically compositional system (L18-1)

Copied to clipboard

Challenge: Several studies have proposed linguistic models to describe sign languages, but none have succeeded to describe the specificities of SL.
Approach: They propose a linguistic approach to formalize the sign language (SL) they propose to take into account linguistic properties of the SL while respecting constraints of a modelisation process.
Outcome: The proposed model takes into account linguistic properties of the sign language while respecting constraints of a modelisation process.
WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language (2022.acl-short)

Copied to clipboard

Challenge: Signed Language Processing (SLP) is a major form of NLP, but has been overlooked by the NLP community.
Approach: They leverage existing resources to construct a large-scale dataset of American Sign Language signs annotated with six different phonological properties.
Outcome: The proposed model outperforms existing approaches on signs unobserved during training.
Challenges with Sign Language Datasets for Sign Language Recognition and Translation (2022.lrec-1)

Copied to clipboard

Challenge: Sign Languages are the primary means of communication for at least half a million people in Europe . however, the development of SL recognition and translation tools is slowed down by resource scarcity and data formats are not suitable for machine learning.
Approach: They propose a framework to unify available resources and facilitate SL research for different languages.
Outcome: The proposed framework is based on a set of ELAN files and returns textual and visual data ready to train SL recognition and translation models.
CLeLfPC: a Large Open Multi-Speaker Corpus of French Cued Speech (2022.lrec-1)

Copied to clipboard

Challenge: Cued Speech is a visual communication system developed for deaf people to complement speechreading at the phonetic level with hands.
Approach: They describe a visual communication mode that uses handshapes in different placements near the face and mouth movements to make the phonemes of spoken language look different from each other.
Outcome: The proposed system is based on 4 hours of audio and video recordings of 23 participants.
MEDIAPI-SKEL - A 2D-Skeleton Video Database of French Sign Language With Aligned French Subtitles (2020.lrec-1)

Copied to clipboard

Challenge: MEDIAPI-SKEL is a 2D-skeleton database of french Sign Language videos aligned with French subtitles.
Approach: They propose a 2D-skeleton database of french Sign Language videos aligned with French subtitles and a vocabulary size of 17k tokens.
Outcome: The proposed corpus contains 27 hours of video of body, face and hand keypoints, aligned to subtitles with a vocabulary size of 17k tokens.
Deep JSLC: A Multimodal Corpus Collection for Data-driven Generation of Japanese Sign Language Expressions (L18-1)

Copied to clipboard

Challenge: Existing technologies for CG-supported data display are not able to depict all relevant features of a natural signing sequence such as facial expression, spatial references or inter-sign movement.
Approach: They collected a corpus of Japanese Sign Language sentences for deep neural network learning.
Outcome: The proposed model could be used to train language features in Japanese Sign Language (JSL)
Elicitation protocol and material for a corpus of long prepared monologues in Sign Language (L18-1)

Copied to clipboard

Challenge: elicitation of long discourses is difficult in Sign Language, and is often a problem . e.g., elicitation of long texts is a technique that can be used to collect long discourse .
Approach: They propose a protocol and two tasks to collect long discourse in Sign Language . they propose to ensure both are collected and prepared in the language .
Outcome: The proposed protocol improves the produced data and the results of a test with LSF informants.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations