British Sign Research Articles

Application of AI in Turkish Sign Language Translation: A Case Study of its Use and Purpose

In Turkey, around 3 million people have hearing impairments, and the shift to digital platforms during the pandemic has worsened accessibility challenges as websites and apps often ignore their needs. Research shows that 50% of hearing-impaired individuals struggle to understand written text due to Turkish Sign Language being their first language, with Turkish serving as a second language. Differences in grammar between Turkish and Turkish Sign Language, along with a limited sign language vocabulary, further hinder comprehension. To solve this, we developed AI-powered sign language translation systems that allow people who are deaf or hard of hearing to access digital content in Turkish Sign Language. SignForDeaf's system translates text into sign language videos using Natural Language Processing (NLP) and generates seamless videos with smooth word transitions. Currently, this system supports Turkish Sign Language, with future plans to include other languages like Arabic, American, British, and Finnish Sign Language. The system was designed in collaboration with sign language experts to ensure accuracy and an inclusive development of a digital environment.

Sign duration and signing rate in British Sign Language, Dutch Sign Language and Swedish Sign Language

In this article, we look at sign duration and signing rate in corpora of three sign languages – British Sign Language (BSL), Dutch Sign Language (NGT), and Swedish Sign Language (STS). We investigate whether token frequency and sociolinguistic variables (e.g., age, gender, region) influence the production rate of signing. Following Zipf’s law of abbreviation, we see that a sign’s duration is negatively correlated with its frequency. Both sign duration and signing rate are found to correlate with signer age, in that older signers have longer durations and lower rates than younger signers. Signers' gender, family (deaf or hearing), and age of exposure have no effect on duration or signing rate. For NGT and STS, there is no effect of region on either duration or rate. However, in the BSL data, duration and signing rate vary with region. The overall findings align with previous work on spoken languages, particularly that frequency and aging are correlated with word length and production rate, thus demonstrating such patterns across modalities of language.

Design a smart platform translating Arabic sign language to English language

Sign language is the only means of communication for deaf and hearing-disabled people in their communities. It uses body language and gestures, such as hand shapes and facial expressions, to convey a message. It is important to note that sign language is specific to the region; that is, Arabic sign language (ArSL) is different from English sign language. Therefore, this research proposes a way to improve the translation of ArSL using a new artificial intelligence (AI) architecture. Specifically, a convolutional neural network (CNN) based on fine-tuning of the SSD-ResNet50 V1 FPN is applied to build a real-time ArSL recognition and translation system with fast and accurate results. The proposed AI architecture can provide translation of sign language in real-time to enhance communication in the deaf community. We achieved an average F-score of 86% and an average accuracy of 94%.

Exploring positional and dimensional aspects of topographic space for advanced-level British Sign Language learners

Abstract This study investigates how British Sign Language (BSL) learners develop positional and dimensional aspects of topographic space. The teaching of BSL has been occurring at an increasing rate, and many people are learning to use BSL to the advanced levels, which are generally referred to in the UK as BSL Levels 4 and 6 and are loosely equivalent to pre-C1 (advanced) and C1 (proficient), respectively, on the Common European Framework for Reference (Languages) scale. Spatial grammar is a crucial aspect of BSL (Brennan 1992), and this article provides insight into issues related to learning how to use topographic space, a feature of spatial grammar whereby real-world referent locations are replicated in the signing production. This study of L2 advanced learners of BSL explores the numbers and types of errors that are made when applying topographic features into their signing, with a particular focus on positioning and dimensionality aspects. Two scenarios are used do this: classroom layouts (Task 1) and a courtroom layout (Task 2). The study concludes with reflections on how BSL teachers can support L2 learners in improving their development of topographic skills.

Transparency Animations: Trusted Research Environments, Data Linkage and Synthetic Data

BackgroundWith funding from HDR UK, Research Data Scotland (RDS) commissioned award-winning production company Media Co-op to create three short graphic animations targeted at both researchers and members of the public, building on our existing text-based content by introducing educational resources in a new format. These videos highlight three topics that have generated substantial interest among RDS users: Trusted Research Environments, data linkage and synthetic data. IntroductionFounded in 2021, RDS’s brand values centre on providing clarity, encouraging simplicity and building public trust. These values closely align with the aims of the HDR UK Transparency Standards, particularly around transparent application processes and criteria (Standard 2) and consideration for target audiences (Standard 4). MethodsRDS worked with creative agency Media Co-op to develop the animations with input from both subject matter experts and members of the public. Data experts were consulted throughout the project to ensure information accuracy. Two rounds of feedback from the Scotland Talks Data public panel, run jointly by RDS and the Scottish Centre for Administrative Data Research (SCADR), were also incorporated with the aim of ensuring appropriate and accessible language. ResultsThe resulting animations explain complex topics in layperson terms to aid comprehension. Each video also has a corresponding British Sign Language (BSL) version to aid wider accessibility. We anticipate that these videos will ensure both researchers and the public can glean a clearer understanding of these intricate concepts. ConclusionsBy applying a Creative Commons Non-Commercial Share Alike 4.0 license to all three videos, we intend for all partner organisations across the UK to be able to reuse or share these videos with their respective audiences. The more organisations share these videos, the more we will build a collective understanding of these complex topics. The final animations can be viewed on the RDS YouTube channel: How is data kept secure? What is data linkage? What is synthetic data? To honour our commitment to creating accessible content, BSL versions of all three animations are also available: How is data kept secure? (BSL) What is data linkage? (BSL) What is synthetic data? (BSL)

British Sign Language and its Role in Dentistry

Hearing impairments affect up to 1.57 billion individuals globally, and 11 million people within the UK. Worldwide, 60% of hearing loss in children is due to preventable causes. Types of hearing loss vary in their aetiology and severity; however, all can negatively affect an individual's quality of life. The general health of those within the deaf population has been shown to be poorer than that of the general population, with under-diagnosis and under-treatment of chronic conditions putting individuals at risk of preventable ill-health. Deaf individuals experience greater problems in accessing healthcare, with a lack of British Sign Language (BSL), deafness awareness training and other communication aids being identified as barriers in such settings. With respect to dental health, deafness can result in poorer oral hygiene and greater dental caries. Communication issues faced at the dentist include being called from the waiting room, communicating with the dental team, mask wearing and background noise in the surgery. British Sign Language is a visual and spatial language, using movements of the hands, body, face and head. With its own grammar, syntax, idioms and regional variations, it is recognized as an official language in England, Wales and Scotland. This article provides a general background on hearing loss, its influence on general and dental health, an introduction to BSL, and hopes to encourage the general dental practitioner to seek further training in BSL. CPD/Clinical Relevance: To aid in effective communication with patients who have hearing loss, a knowledge of BSL would be helpful.

Interactional Infrastructure across Modalities: A Comparison of Repair Initiators and Continuers in British Sign Language and British English

Abstract: Minimal expressions are at the heart of interaction: Interjections like "Huh?" and "Mhm" keep conversations flowing by establishing and reinforcing intersubjectivity among interlocutors. Crosslinguistic research has identified that similar interactional pressures can yield structurally similar words (e.g., to initiate repair across languages). While crosslinguistic comparisons that include signed languages remain uncommon, recent work has revealed similarities in discourse management strategies among signers and speakers that share much of their cultural background. This study contributes a crossmodal comparison of repair initiators and continuers in speakers of English and signers of British Sign Language (BSL). We combine qualitative and quantitative analyses of data from sixteen English speakers and sixteen BSL signers, resulting in the following: First, the interactional infrastructure drawn upon by speakers and signers overwhelmingly relies on behaviors of the head, face, and body; these are used alone or sometimes in combination with verbal elements (i.e., spoken words or manual signs), while verbal strategies alone are rare. Second, discourse management strategies are remarkably similar in form across the two languages: A held eye gaze or freeze-look is the predominant repair initiator and head nodding the main continuer. These results suggest a modality-agnostic preference for visual strategies that do not occupy the primary articulators, one that we propose is founded in recipiency; people maintain the flow of communication following principles of minimal effort and minimal interruption.

Spatial–temporal feature-based End-to-end Fourier network for 3D sign language recognition

Most dynamic sign word misclassifications are caused by redundant spatial–temporal (SPT) feature pruning that lacks language semantic and temporal dependencies. SPT feature recognition is one of the important aspects for the evaluation of the misclassification of dynamic sign words. The redundant pruning of SPT feature space influences the language model of sign confusion, model complexity, and SPT feature similarity. The purpose of this article is to develop a new multi-scale SPT feature-based dynamic sign word recognition approach via a low-cost feature selection method (FS) and End-to-end Fourier convolution neural network (EFCNN). Instead of a sensor fusion technique for obtaining frame position alignment, in the EFCNN, new 3D frame position and coordinates are determined using a pixel weighting and alignment function of the first and succeeding 25 spatial intensities of the 3D video changes across hand motion. The new spatial weight and the original spatial coordinates are fused and truncated in the Fourier domain. We generate the temporal dependence of the fused features. A feature selection known as the FS-EFCNN is introduced to select compact features with a preserved language meaning. Five state-of-the-art feature selection methods, namely Infinite FS (InFS), Relief FS, Fisher, MIM, ILFS, and ensemble FS-EFCNN were deployed to guide and optimize the learning performance of EFCNN. The experimental result analysis highlighted the improved results of the FS-EFCNN method with the best accuracy of 99.86%, 99.89%, and 90.69% on 3D American Sign Language, British Sign Language, and Greek Sign Language data sets, respectively.

Sign Language Analysis Using CNN Algorithm

Sign language is a rich and diverse mode of communication used by Deaf and hard of-hearing communities around the world. This paper presents a comprehensive analysis of sign language, focusing on its linguistic and gestural elements. Our study encompasses an exploration of the structural properties of sign languages, their historical evolution, and the cognitive and neural mechanisms underlying sign language processing. We begin by providing an overview of sign language as a natural and fully developed language with its own syntax, semantics, and phonological features. Drawing from various sign languages, including American Sign Language (ASL), British Sign Language (BSL), and others, we investigate the grammatical aspects and iconicity within signs. Furthermore, we examine the role of facial expressions and non-manual markers in conveying essential linguistic information. This analysis also delves into the historical and cultural dimensions of sign languages, shedding light on the evolution of sign languages and the influence of Deaf culture on their development. It highlights the importance of recognizing sign languages as unique cultural and linguistic entities, distinct from spoken languages. Keywords:Computer Vision; Convolutional Neural Networks; Sign Language Recognition

Viewing angle matters in British Sign Language processing

The impact of adverse listening conditions on spoken language perception is well established, but the role of suboptimal viewing conditions on signed language processing is less clear. Viewing angle, i.e. the physical orientation of a perceiver relative to a signer, varies in many everyday deaf community settings for L1 signers and may impact comprehension. Further, processing from various viewing angles may be more difficult for late L2 learners of a signed language, with less variation in sign input while learning. Using a semantic decision task in a distance priming paradigm, we show that British Sign Language signers are slower and less accurate to comprehend signs shown from side viewing angles, with L2 learners in particular making disproportionately more errors when viewing signs from side angles. We also investigated how individual differences in mental rotation ability modulate processing signs from different angles. Speed and accuracy on the BSL task correlated with mental rotation ability, suggesting that signers may mentally represent signs from a frontal view, and use mental rotation to process signs from other viewing angles. Our results extend the literature on viewpoint specificity in visual recognition to linguistic stimuli. The data suggests that L2 signed language learners should maximise their exposure to diverse signed language input, both in terms of viewing angle and other difficult viewing conditions to maximise comprehension.

Silent Expressions Unveiled: Deep Learning for British and American Sign Language Detection

Sign language is an efficient means of communication for the hearing impaired. The main goal of this research is to recognize both American and British sign languages using computer vision algorithms and neural networks. Our work addresses the critical need for inclusive and accessible communication for the Deaf community. For the study, we compiled a large dataset of her ASL and BSL gestures. Preprocess the data to improve feature extraction and reduce noise. Our model architecture uses a convolutional neural network (CNN) to capture the temporal patterns of finger gestures. This allows you to use Mediapipe keypoint detection within your model. The end result is a comprehensive model that can accurately and quickly recognize and classify sign language gestures. We further improve the usability of the system by integrating keyword recognition into the model, allowing sign language sentences to be decoded and translated into text. Our test results demonstrate how well our deep learning strategy works to achieve high efficiency and accuracy in both ASL and BSL detection. This program helps bridge the gap between those who use sign language and those who do not. Our new approach not only accurately recognizes American and British sign language, but also seamlessly integrates real-time feedback to help users make immediate improvements to improve their sign language skills. We can do better. Moreover, our approach is flexible enough to be used in a variety of settings, ensuring its usefulness in educational environments and providing sign language learners with a fun and dynamic learning environment. Explore and exploit the full potential of Mediapipe Keypoint using CNNs and also leverage the efficiency of computer vision.

The Beginnings of Research on British Sign Language

The Beginnings of Research on British Sign Language

Cultural competence in NHS hearing aid clinics: a mixed-methods case study of services for Deaf British sign language users in the UK

BackgroundThis study identified and explored how National Health Service (NHS) hearing aid clinics address cultural competence concerning Deaf British Sign Language (BSL) users. This was approached by (i) investigating how organisational processes meet the needs of Deaf signers from a hospital and hearing aid clinic perspective, (ii) analysing policies and guidelines to investigate if they equip practitioners to meet the needs of Deaf signers and (iii) exploring with practitioners who work in hearing aid clinics about their experiences of working with Deaf signers.MethodsThis study utilised a mixed-methods multiple case study design, incorporating documentary analysis and semi-structured interviews. Interview analysis was conducted using Reflexive Thematic Analysis (RTA). The research encompassed two hearing aid clinics in separate hospitals, producing 19 documents and eight interviews (four at each site) with audiologists ensuring a representative mix of professional experience levels.ResultsFour themes emerged from the integrated analysis: (1) Understanding Deaf signers; (2) Communicating with Deaf signers; (3) Barriers and Facilitators and (4) Service improvement. A noticeable gap in understanding BSL as both a language and a cultural system was apparent across various policies, strategies, training programmes and staff expertise. Over-reliance on interpreters provided a false sense of accessibility and most participants felt tentative to engage directly with Deaf signers. Positive practices observed at Sites A and B encompassed accurate identification of patients as Deaf signers, improved interpreter availability, communication methods, enhanced training and the encouragement of professional self-awareness.ConclusionThis is the first study that explores cultural competence of hearing aid clinics and its staff concerning Deaf signers in the UK. The results show both clinics require development to become an effective provider for culturally Deaf signers. Examples of how to design culturally competent practices have been provided to assist hearing aid clinics. The findings may be applicable to other underrepresented groups who are not typical users of conventional, acoustic hearing aids provided by the NHS.

“What have YOU done in the past few years?” Deaf BSL users’ experiences of caring for people with dementia during COVID-19

PurposeDeaf people, who are British Sign Language (BSL) users, are, at times, carers for their parent or spouse when they have dementia. This can be a challenging role for the wider population, but if the common language in service provision is not one you share, then this care can be impacted by the lack of formal structures that support the Deaf caring role. This study aims to explore the experiences of Deaf carers supporting people with dementia, in an unpaid role, during the COVID-19 pandemic to understand more about their potential support preferences.Design/methodology/approachOnline interviews with seven Deaf carers sharing their experiences of supporting their family member with dementia happened during the first year of the COVID-19 pandemic. Interpretive phenomenological analysis was used to qualitatively examine each Deaf carers’ stories.FindingsFindings included Deaf carers’ lack of access to information, surrendering their autonomy to hearing family members to communicate with health-care professionals, with overarching isolation within local communities and online. Findings show a widespread infrastructural failure to meet the linguistic and specific support needs of this minority population.Research limitations/implicationsSeven Deaf carers took part in this study. This means the findings may not be generalisable.Practical implicationsHealth-care professionals and social care structures need to develop robust clear communication pathways for Deaf carers to receive the support needed to provide effective care.Social implicationsIf health-care professionals undertake training about Deaf people and BSL, that will mean Deaf carers will receive effective support to be able to care for a person living with dementia. This means that their Deaf identity will be recognised within the mainstream and the care provided will be much more effective for the person with dementia.Originality/valueTo the best of the authors’ knowledge, these are the first interviews undertaken with Deaf carers of people with dementia during the COVID-19 pandemic and its subsequent lockdowns. Understanding everyday barriers and social care limitations in terms of language access will enable Deaf carers to assert their rights and for care professionals to adapt their communication to match the individuals involved in the care package.

The social structure of signing communities and lexical variation: A cross-linguistic comparison of three unrelated sign languages

Claims have been made about the relationship between the degree of lexical variation and the social structure of a sign language community (e.g., population size), but to date there exist no large-scale cross-linguistic comparisons to address these claims. In this study, we present a cross-linguistic analysis of lexical variation in three signing communities: Kata Kolok, Israeli Sign Language (ISL) and British Sign Language (BSL). Contrary to the prediction that BSL would have the lowest degree of lexical variation because it has the largest population size, we found that BSL has the highest degree of lexical variation across the entire community (i.e., at the global level). We find, however, that BSL has the lowest degree of lexical variation at the local level, i.e., within clusters of participants who group most similarly lexically. Kata Kolok and ISL, on the other hand, exhibit less of a distinction between variation at the global and local levels, suggesting that lexical variation does not pattern as strongly within subsets of these two communities as does BSL. The results of this study require us to reassess claims made about lexical variation and community structure; we need to move towards an approach of studying (lexical) variation which treats communities equally on a theoretical level and which respects the unique social-demographic profile of each community when designing the analysis by using a community-centered approach.

Counselling psychologists working in Human rights & social justice

We argue in this paper that counselling psychologists have been championing human rights and social justice in different ways and since the Division was first being considered. We draw on counselling psychology historical literature, and from responses from our colleagues within the profession. As part of our preparation for this paper we put out a call to counselling psychologists through the Division of Counselling Psychology to invite our colleagues to share with us the work they are engaged in relating to Human Rights and Social Justice. In this paper we share themes from the responses we received on the various areas covering human rights aspects of counselling psychology and social justice, for example championing climate justice, equality, diversity, and inclusion. Our call was operationalised through a Questback survey which comprised of 10 questions. These included demographic questions, questions which enquired about areas of respondent’s work which covered human rights aspects of psychology and social justice. The responses for example included mental health work with refugees, asylum seekers, trafficked people, torture survivors; Black and Minoritised Ethnic adults aged 18+; people from what one respondent noted as ‘the profoundly deaf community’ who use BSL (British Sign Language) as their first language; and other aspects of equality, diversity, and inclusion. Furthermore, we enquired whether our counselling psychology respondents had faced experiences in which they have wanted to engage with human rights-based/focused work but had been prevented from doing this. These questions could be responded to through qualitative responses, and we offer example of quotes from respondents throughout different sections of this paper. The respondents also replied at a specific time period and the issues raised might differ if the questionnaire was answered at an earlier or later time period.

Recognizing British Sign Language Using Deep Learning: A Contactless and Privacy-Preserving Approach

Sign language is utilized by deaf-mute to communicate through hand movements, body postures, and facial emotions. The motions in sign language comprise a range of distinct hand and finger articulations that are occasionally synchronized with the head, face, and body. Automatic sign language recognition (SLR) is a highly challenging area and still remains in its infancy compared with speech recognition after almost three decades of research. Current wearable and vision-based systems for SLR are intrusive and suffer from the limitations of ambient lighting and privacy concerns. To the best of our knowledge, our work proposes the first contactless British sign language (BSL) recognition system using radar and deep learning (DL) algorithms. Our proposed system extracts the 2-D spatiotemporal features from the radar data and applies the state-of-the-art DL models to classify spatiotemporal features from BSL signs to different verbs and emotions, such as Help, Drink, Eat, Happy, Hate, and Sad. We collected and annotated a large-scale benchmark BSL dataset covering 15 different types of BSL signs. Our proposed system demonstrates highest classification performance with a multiclass accuracy of up to 90.07% at a distance of 141 cm from the subject using the VGGNet model.

Deaf professionals’ perceptions of 'trust' in relationships with signed language interpreters

The concept of ‘trust’ is frequently used when discussing the working relationship between deaf signers and signed language interpreters, with interpreters often claiming that trust is a prerequisite to a successful interaction. This paper presents original data from an in-depth research project which used collaborative autoethnography to gather the experiences of seven deaf academics who work regularly with British Sign Language (BSL) interpreters, who interpret between BSL and spoken English, to analyse the concept of ‘trust’ in our working relations with BSL interpreters. We found that ‘trust’ is not a useful or productive concept for our interpersonal and professional aims. Instead, we outline multiple ways in which deaf academics can assess and evaluate interpreters’ values, competencies, and performance without relying on ‘trust’. Our findings provide an important, powerful and under-explored perspective on the working relations between deaf academics and interpreters. We suggest these findings can be applied by deaf BSL signers and interpreters in contexts beyond academia, and constitute an important contribution to the literature on interpreting.

Now you see them, now you don’t: Professional recognition of specialist professionals working with Deaf British Sign Language parents in child safeguarding

This paper concerns parenting assessments which are integral to child-safeguarding professional processes in England, and which involve Deaf parents whose primary language is British Sign Language (BSL). In an under-researched area of social work, the research aim was to contribute to the existing literature by eliciting the practice wisdom of specialist professionals. Specifically, it draws upon their linguistic and cultural knowledge of the Deaf community when they are involved in parenting assessments with Deaf parents who are subject to safeguarding concerns. Data about these professionals’ actual experiences of navigating Deaf cultural-competency in contemporary child protection practices were collected through seven video-recorded, semi-structured interviews conducted in BSL. Using interpretive phenomenological analysis, data were analysed in their source language (BSL). This article focusses on one key theme, termed ‘Professional Recognition’, which incorporates a) the identification of specialist roles and b) the impact of referral processes and protocols on assessment outcomes. The findings highlight participants’ perspectives on the benefits and disadvantages of their specialist role in this context. Although their brokerage skills, cultural competence, linguistic fluency and specialist knowledge of the Deaf community are highly regarded and valued by some colleagues, there is insufficient recognition of their existence by the majority. Secondly, participants are concerned by the inefficiency and inconsistency of the referral processes and protocols which they consider have adverse effects on assessment outcomes, and consequently the parents involved. The BSL translation of this article is available in the supplementary material .

Attitudes towards age variation and language change in the British deaf community

There are age-related differences in signers of British Sign Language (BSL) and evidence that BSL is changing. Here we explore attitudes of BSL signers towards age-related differences and language change. We studied interview data from the BSL Corpus (Schembri et al., 2014) from 80 signers from four regions in the U.K. We carried out a thematic analysis following Braun and Clarke (2006) on responses to questions related to age variation and language change. Findings reveal signers were aware of variation and change in BSL, which also align with linguistic behaviour. Some variation and change was deemed more acceptable than others, e.g. signs for new concepts. Other changes were seen as a threat to BSL's vitality. We explore these attitudes, looking particularly at language endangerment and vitality within minority languages.