skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: The Sem-Lex Benchmark: Modeling ASL Signs and their Phonemes
Sign language recognition and translation technologies have the potential to increase access and inclusion of deaf signing communities, but research progress is bottlenecked by a lack of representative data. We introduce a new resource for American Sign Language (ASL) modeling, the Sem-Lex Benchmark. The Benchmark is the current largest of its kind, consisting of over 84k videos of isolated sign productions from deaf ASL signers who gave informed consent and received compensation. Human experts aligned these videos with other sign language resources including ASL-LEX, SignBank, and ASL Citizen, enabling useful expansions for sign and phonological feature recognition. We present a suite of experiments which make use of the linguistic information in ASL-LEX, evaluating the practicality and fairness of the Sem-Lex Benchmark for isolated sign recognition (ISR). We use an SL-GCN model to show that the phonological features are recognizable with 85% accuracy, and that they are effective as an auxiliary target to ISR. Learning to recognize phonological features alongside gloss results in a 6% improvement for few-shot ISR accuracy and a 2% improvement for ISR accuracy overall. Instructions for downloading the data can be found at https://github.com/leekezar/SemLex.  more » « less
Award ID(s):
1918556 1625793 1918252 2234787
PAR ID:
10481698
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
ACM
Date Published:
Journal Name:
ASSETS: ACM SIGACCESS Conference On Computers And Accessibility
Issue:
34
ISBN:
9798400702204
Page Range / eLocation ID:
1 - 10
Subject(s) / Keyword(s):
American Sign Language, sign language, phonology, islr, sign recognition
Format(s):
Medium: X
Location:
New York NY USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, The Journal of Deaf Studies and Deaf Education)
    null (Ed.)
    Abstract ASL-LEX is a publicly available, large-scale lexical database for American Sign Language (ASL). We report on the expanded database (ASL-LEX 2.0) that contains 2,723 ASL signs. For each sign, ASL-LEX now includes a more detailed phonological description, phonological density and complexity measures, frequency ratings (from deaf signers), iconicity ratings (from hearing non-signers and deaf signers), transparency (“guessability”) ratings (from non-signers), sign and videoclip durations, lexical class, and more. We document the steps used to create ASL-LEX 2.0 and describe the distributional characteristics for sign properties across the lexicon and examine the relationships among lexical and phonological properties of signs. Correlation analyses revealed that frequent signs were less iconic and phonologically simpler than infrequent signs and iconic signs tended to be phonologically simpler than less iconic signs. The complete ASL-LEX dataset and supplementary materials are available at https://osf.io/zpha4/ and an interactive visualization of the entire lexicon can be accessed on the ASL-LEX page: http://asl-lex.org/. 
    more » « less
  2. ; ; ; ; ; (, Proceedings of the European Symposium for Artificial Neural Networks)
    Like speech, signs are composed of discrete, recombinable features called phonemes. Prior work shows that models which can recognize phonemes are better at sign recognition, motivating deeper exploration into strategies for modeling sign language phonemes. In this work, we learn graph convolution networks to recognize the sixteen phoneme "types" found in ASL-LEX 2.0. Specifically, we explore how learning strategies like multi-task and curriculum learning can leverage mutually useful information between phoneme types to facilitate better modeling of sign language phonemes. Results on the Sem-Lex Benchmark show that curriculum learning yields an average accuracy of 87% across all phoneme types, outperforming fine-tuning and multi-task strategies for most phoneme types. 
    more » « less
  3. ; ; (, Association for Computational Linguistics)
    Vlachos, Andreas; Augenstein, Isabelle (Ed.)
    We use insights from research on American Sign Language (ASL) phonology to train models for isolated sign language recognition (ISLR), a step towards automatic sign language understanding. Our key insight is to explicitly recognize the role of phonology in sign production to achieve more accurate ISLR than existing work which does not consider sign language phonology. We train ISLR models that take in pose estimations of a signer producing a single sign to predict not only the sign but additionally its phonological characteristics, such as the handshape. These auxiliary predictions lead to a nearly 9% absolute gain in sign recognition accuracy on the WLASL benchmark, with consistent improvements in ISLR regardless of the underlying prediction model architecture. This work has the potential to accelerate linguistic research in the domain of signed languages and reduce communication barriers between deaf and hearing people. 
    more » « less
  4. ; ; ; ; ; (, ESANN 2023 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning)
    Like speech, signs are composed of discrete, recombinable features called phonemes. Prior work shows that models which can recognize phonemes are better at sign recognition, motivating deeper exploration into strategies for modeling sign language phonemes. In this work, we learn graph convolution networks to recognize the sixteen phoneme “types” found in ASL-LEX2.0. Specifically, we explore how learning strategies like multi-task and curriculum learning can leverage mutually useful information between phoneme types to facilitate the remodeling of sign language phonemes. Results on the Sem-Lex Benchmark show that curriculum learning yields an average accuracy of 87% across all phoneme types, outperforming fine-tuning and multi-task strategies for most phonemetypes. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al (, 37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks)
    Sign languages are used as a primary language by approximately 70 million D/deaf people world-wide. However, most communication technologies operate in spoken and written languages, creating inequities in access. To help tackle this problem, we release ASL Citizen, the first crowdsourced Isolated Sign Language Recognition (ISLR) dataset, collected with consent and containing 83,399 videos for 2,731 distinct signs filmed by 52 signers in a variety of environments. We propose that this dataset be used for sign language dictionary retrieval for American Sign Language (ASL), where a user demonstrates a sign to their webcam to retrieve matching signs from a dictionary. Through our generalizable baselines, we show that training supervised machine learning classifiers with our dataset achieves competitive performance on metrics relevant for dictionary retrieval, with 63% accuracy and a recall-at-10 of 91%, evaluated entirely on videos of users who are not present in the training or validation sets. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email