Search Results (77)

Automatic sign language generation has the potential to support information accessibility for deaf and hard-of-hearing individuals. Generating sign language pose sequences from natural language text can serve as an intermediate representation for avatar-based sign language expression and sign language video synthesis. However, text-to-sign pose generation is challenging because sign language conveys meaning through both manual movements and non-manual signals, while requiring temporally coherent motion over local and sentence-level contexts. In addition, text length does not directly correspond to the number of pose frames required for sign language expression. To address these issues, this study proposes a text-to-Korean Sign Language (KSL) pose generation model based on non-manual signal conditioning and multi-scale temporal refinement. The proposed framework integrates a text encoder, pose decoder, non-manual signal conditioning, multi-scale temporal refinement, and length prediction/blending. The model generates normalized 58-joint KSL keypoint sequences from morpheme-level text inputs and jointly optimizes pose reconstruction, motion continuity, bone consistency, PCK-aware precision, non-manual signal prediction, and length consistency. Experimental results on a KSL text–pose dataset show that the proposed model outperforms text-only and Transformer-based baselines. Compared with the Transformer text-to-pose baseline, the proposed model reduced MPJPE from 0.408236 to 0.316366 and Pose MAE from 0.165473 to 0.128570. It also improved PCK@0.05 from 0.136090 to 0.163928 and reduced the length relative error from 0.221455 to 0.127152. In particular, the best-threshold non-manual F1 substantially increased from 0.010859 to 0.494566. These results suggest that text-based KSL pose generation should jointly consider non-manual expressions, length consistency, and long-term temporal motion structure rather than relying only on frame-wise keypoint prediction. However, the reported improvements should be interpreted as coordinate- and label-level evidence, not as a complete validation of linguistic meaningfulness or real-world accessibility. Full article

The linguistic landscape is a significant aspect of the cultural landscape and heritage. Istria, a region and peninsula located in the Republic of Croatia, has experienced various influences over the years that have shaped language use, impacting the linguistic landscape and the identity of the local population. This paper aims to investigate how the linguistic and spatial identity of the people in Istria has been represented in the region’s cultural landscape during two comparative periods: the turn of the 20th century (the local population’s fight for their national language against the languages imposed by the European powers that governed this region—Italy and Austria) and the turn of the 21st century (the status of minorities in the present Croatian region of Istria). This diachronic research employs a cross-sectional method to compare findings and establish cause-and-effect relationships. This study involves analyzing linguistic data from historical postcards, conducting field studies, and using the pin placement feature on Google Maps to assess recent periods. This research identified Italian and Croatian as the dominant languages during different periods, with English being increasingly prevalent in contemporary times. The results demonstrated that the spatial identity of the Italian minority community is strongly reflected in the linguistic landscape, primarily due to bilateral interstate agreements. Full article

Urban ethnic enclaves are historically layered cultural landscapes whose public signage encodes community vitality, power relations, and cultural identity in ways that conventional land-use inventories cannot capture. Addressing the absence of scalable, longitudinal computational methods for monitoring such at-risk landscapes, this study develops a reproducible digital-mapping pipeline that operationalises linguistic-landscape analysis as a cultural-heritage monitoring tool for heritage-sensitive land-use planning. Taking Daerim-dong—Seoul’s primary Joseonjok (Korean Chinese) enclave—as a case, we process 38,640 Kakao Map Road View images across 17 annual cross-sections (2008–2024). The pipeline integrates four methodological components: a bounded Spatial Weighting Correction that adjusts for uneven historical coverage; zero-shot semantic sign-function classification using the Qwen2-7B-Instruct model; an exploratory Difference-in-Differences design probing the 2016–2017 THAAD geopolitical disruption; and a Boundary Permeability Ratio (BPR) for tracking enclave edge dynamics. The results document a three-phase trajectory—rapid bilingual expansion (2008–2016), stabilisation (2016–2019), and a COVID-period contraction (2019–2024)—and show that raw sign-count metrics can systematically overstate minority-language decline during economic crises once crisis-period signage is isolated. The BPR is presented as a candidate leading indicator of enclave contraction whose operational thresholds remain to be calibrated through multi-enclave validation. As a methodological proof-of-concept, the study illustrates how computational street-view analysis can support cultural-landscape governance, offering urban planners and heritage managers an actionable, transparent baseline for monitoring at-risk multicultural urban landscapes. Full article

The multilingualism found in many countries, as well as within professional groups, complicates verbal communication, as both communicating parties are required to know all the languages used. This problem is exacerbated by the fact that languages are often mixed during communication. Avatars can be used to communicate with deaf people by simulating the behavior of sign language users. This paper presents a digital sign language avatar built on a language-agnostic, multimodal animation pipeline that decouples linguistic input from animation, combining skeletal body and hand motion with facial blendshape animation as independent modalities. It also presents a methodology for assessing its quality with the participation of experts (i.e., professional sign language interpreters) and the corresponding research results. The average quality rating of the avatar interface by the experts was 5.5 on a 7-point Likert scale, indicating its potential for practical use. At the same time, the research identified opportunities to improve the naturalness of movement and the consistency of gesture transitions. Full article

Early patterning skills, particularly those involving linear repeating patterns, are well-established predictors of mathematical development. This relationship has not yet been investigated in visually oriented deaf and hard-of-hearing (DHH) children. It also remains unclear whether a two-dimensional pattern structure contributes to predicting numerical skills in children at the time of school entry. The present study investigates the relationship between repeating patterning skills in two formats (linear and circular) and numerical skills in a total of 38 DHH and typically hearing children. Language competence was additionally assessed in the DHH group to account for its linguistic heterogeneity. In the DHH and hearing groups, repeating patterning skills in each format strongly predicted numerical skills. Among DHH children, prior language experience played a more decisive role in mathematical development. The circular format emerged as a particularly strong predictor for typically hearing children. DHH children, especially those with sign language experience, perform equally well with both formats, and it is argued that this is due to their enhanced visuospatial skills. Full article

This study presents a comprehensive review of more than 100 research papers on sign language recognition (SLR) published between 2020 and 2026. The analysis focuses on deep learning approaches applied to video-based SLR, including spatiotemporal feature extraction, temporal modeling, attention mechanisms, motion-based representations, hybrid frameworks, transfer learning methods and other methods. Particular attention is given to how these methods model spatiotemporal dynamics and capture subtle gesture characteristics in sign language communication. The review highlights several recent developments, such as the introduction of specialized datasets, the emergence of real-time recognition systems, and the integration of multimodal fusion strategies. At the same time, persistent challenges remain, including data scarcity in low-resource sign languages, limited linguistic standardization of datasets, and insufficient model interpretability. The findings underline the importance of developing scalable and generalizable models capable of handling diverse datasets and user variability. The distinct contributions of this review are fourfold: (1) a comprehensive synthesis of over 100 studies published between 2020 and 2026, covering the full spectrum of deep learning architectures for video-based SLR; (2) a structured six-category taxonomy enabling systematic cross-architectural comparison; (3) a comprehensive focus on low-resource sign languages, which remain underrepresented in the existing literature; and (4) a critical analysis of the current benchmark landscape for low-resource sign languages, identifying key gaps and outlining strategic directions for future dataset development. These contributions are intended to guide further research toward more robust, inclusive, and universally applicable SLR systems. Full article

Background: Large language models (LLMs) are increasingly considered as adjuncts for differential diagnostic reasoning, yet their sensitivity to gender-attributed cues in the persona prompt—particularly for neglected tropical diseases (NTDs) and in non-English clinical settings—remains poorly characterised. Objective: The objective of this study was to compare the diagnostic accuracy of one proprietary and three open-weight LLMs for Chagas disease (CD) and visceral leishmaniasis (VL) under paired persona-prompt conditions in which the only manipulated variable was the linguistic gender of the simulated medical persona. Methods: This experimental, paired study evaluated ChatGPT-4o, LLaMA 3 70B, Meditron-70B, and Mixtral 8x7B across 12 cases per disease (n = 24) from real records at a Brazilian teaching hospital. The primary outcome was top-five diagnostic accuracy. A committee of five infectious-disease specialists assessed the biological plausibility of all differentials. Paired comparisons used Wilcoxon signed-rank tests; 95% confidence intervals were calculated using the Wilson-score method. Results: ChatGPT-4o achieved the highest accuracy (CD: 100% under both prompts; VL: 83.3–91.7%). LLaMA 3 70B and Mixtral 8x7B showed moderate performance (41.7–83.3%); the medically fine-tuned Meditron-70B exhibited paradoxically poor accuracy (16.7–25.0%) and the lowest committee-rated plausibility scores. A consistent small numerical trend favoured the female prompt across most model–disease combinations (differences of 0–16.7 percentage points), but no comparison reached statistical significance (all p > 0.05). Conclusions: Gender-attributed persona-prompt variation did not produce a systematic effect on LLM diagnostic accuracy for CD or VL. ChatGPT-4o outperformed the three evaluated open-weight alternatives, and medical-domain fine-tuning did not confer the expected advantage. Expert-validated assessment of hypothesis plausibility should complement target-disease accuracy in clinical LLM evaluation studies, particularly for NTDs. Full article

This paper proposes a unified methodological framework for evaluating heterogeneous approaches to avatar-based sign language visualization. The study introduces a four-dimensional analytical framework based on four independent criteria: (A1) pipeline architecture and degree of automation, (A2) data and annotation requirements, (A3) portability across sign languages and domains, and (A4) integration and accessibility. The framework is applied to a comparative analysis of three dominant paradigms: (P1) notation → animation (e.g., HamNoSys), (P2) writing-based representation → animation (e.g., SignWriting), and (P3) keypoint-based animation and Artificial Intelligence (AI) methods. The comparative assessment shows that the differences between the paradigms are structural and reflect trade-offs among linguistic accuracy, automation level, scalability, and user accessibility, rather than the superiority of any one technology. Overall, the structured comparative framework (A1–A4) is applied for analyzing three paradigms of sign language avatar generation. It enables a systematic evaluation of architectural, data-related, and practical characteristics, highlighting key trade-offs between linguistic accuracy, scalability, and accessibility. Full article

Digital learning tools for American Sign Language (ASL) often lack the interactive depth necessary to engage learners effectively. This paper introduces a novel, browser-based word search game designed to facilitate ASL vocabulary familiarization through gamified interaction. The system employs a two-tier architecture consisting of a React-based frontend and a Flask-based backend. At its core, the application integrates a lightweight, skeleton-based Isolated Sign Language Recognition (ISLR) model, utilizing a Stacked Transformer-based Spatial-Temporal Attention Network to enable real-time webcam-based word entry during the configuration phase. This model, trained on the WLASL-100 dataset, achieves a Top-5 test accuracy of 88.48% with an average model inference latency of 141 ms, enabling real-time webcam input without proprietary hardware. Furthermore, we implement a constraint-satisfaction puzzle generation algorithm that achieves a 100% success rate in creating interlocked, multi-directional grids. Our results demonstrate that merging computer vision with pedagogical game mechanics provides an accessible, high-performance tool for the Deaf and Hard-of-Hearing (DHH) community, bridging the gap between static instruction and active linguistic practice. Full article

Arabic sign language (ArASL) is the primary communication medium for Deaf and hard-of-hearing people across Arabic-speaking communities. Most current ArASL recognition systems are based solely on visual features and do not incorporate linguistic or semantic information that could improve generalization and semantic grounding. This paper introduces CLIP-ArASL, a lightweight CLIP-style multimodal approach for static ArASL letter recognition that aligns visual hand gestures with bilingual textual descriptions. The approach integrates an EfficientNet-B0 image encoder with a MiniLM text encoder to learn a shared embedding space using a hybrid objective that combines contrastive and cross-entropy losses. This design supports supervised classification on seen classes and zero-shot prediction on unseen classes using textual class representations. The proposed approach is evaluated on two public datasets, ArASL2018 and ArASL21L. Under supervised evaluation, recognition accuracies of $99.25\pm 0.14\%$ and $91.51\pm 1.29\%$ are achieved, respectively. Zero-shot performance is assessed by withholding $20\%$ of gesture classes during training and predicting them using only their textual descriptions. In this setting, accuracies of $55.2\pm 12.15\%$ on ArASL2018 and $37.6\pm 9.07\%$ on ArASL21L are obtained. These results show that multimodal vision–language alignment supports semantic transfer and enables recognition of unseen classes. Full article

A persistent challenge for Deaf and Hard-of-Hearing individuals is the communication gap between sign language users and the hearing community, particularly in regions with limited automated translation resources. In Saudi Arabia, this gap is amplified by the reliance on Saudi Sign Language (SSL) and the scarcity of real-time, sentence-level translation systems. This paper presents a real-time system for sentence-level recognition of continuous SSL and direct mapping to natural spoken Arabic. The proposed system operates end-to-end on live video streams or pre-recorded content, extracting spatio-temporal landmark features using the MediaPipe Holistic framework. For classification, the input feature vector consists of 225 features derived from hand and body pose landmarks. These features are processed by a Bidirectional Long Short-Term Memory (BiLSTM) network trained on the ArabSign (ArSL) dataset to perform direct sentence-level classification over a vocabulary of 50 continuous Arabic sign language sentences, supported by an idle-based segmentation mechanism that enables natural, uninterrupted signing. Experimental evaluation demonstrates robust generalization: under a Leave-One-Signer-Out (LOSO) cross-validation protocol, the model attains a mean sentence-level accuracy of 94.2%, outperforming the fixed signer-independent split baseline of 92.07%, while maintaining real-time performance suitable for interactive use. To enhance linguistic fluency, an optional post-recognition refinement stage is incorporated using a large language model (LLM), followed by text-to-speech synthesis to produce audible Arabic output; this refinement operates strictly as post-processing and is not included in the reported recognition accuracy metrics. The results demonstrate that direct sentence-level modeling, combined with landmark-based feature extraction and real-time segmentation, provides an effective and practical solution for continuous SSL sentence recognition in real-time. Full article

This article explores the incorporation of linguistic landscape (LL) studies into English for General Academic Purposes (EGAP) courses, emphasizing its potential to enhance language learning through real-world engagement. This study highlights the growing interest in LL as a sociolinguistic phenomenon that reflects urban multilingualism and cultural dynamics. The goal of this article is to analyze pedagogical benefits of integrating LL into language education, such as fostering critical thinking, pragmatic competence, intercultural awareness among students, and creating situations in which the target language is used in natural communication. Through a case study conducted at the Guangdong Technion–Israel Institute of Technology, the author presents specific classroom activities and reports on how they can be combined with fieldwork conducted by students. The goal of the tasks was to let students analyze language use in public spaces, classifying the surrounding signs into top-down and bottom-up, and informative and regulatory, and discuss how social prestige of languages is reflected in multilingual signs. In documenting written language in public places, creating their own signs and assessing their peers’ work, students were practicing both receptive and productive skills. Most of the work was done in small groups, which contributed to the students’ ability to collaborate with peers. The findings suggest that LL projects can effectively bridge classroom learning with lived language experiences, although challenges remain in implementation due to time constraints and pedagogical ideologies. Full article

Integrating people with hearing disabilities into schools is one of the biggest problems that Latin American societies face. Mexican Sign Language (MSL) is the main language and culture of the deaf community in Mexico. However, its use in formal education is still limited by structural inequalities, a lack of qualified interpreters, and a lack of technology that can support personalized instruction. This study outlines the conceptualization and development of a mobile application designed as an adaptive assistive technology for learning MSL, utilizing a combination of computer vision techniques, deep learning algorithms, and personalized pedagogical interaction. The suggested system uses convolutional neural networks (CNNs) and pose-estimation models to recognize hand gestures in real time with 95.7% accuracy. It then gives the learner instant feedback by changing the difficulty level. A dynamic learning engine automatically changes the level of difficulty based on how well the learner is doing, which helps them learn signs and phrases over time. The Scrum agile methodology was used during the development process. This meant that educators, linguists, and members of the deaf community all worked together to design the product. Early tests show that sign recognition accuracy and indicators of user engagement and motivation show favorable performance and are at appropriate levels. This proposal aims to enhance inclusive digital ecosystems and foster linguistic equity in Mexican education through scalable, mobile, and culturally relevant technologies, in addition to its technical contributions. Full article

Background: Emotions—including joy, sadness, fear, and anger—are fundamental expressions of human experience. For children and adults who are deaf or hard-of-hearing, emotional experiences and communication can differ due to linguistic and communication-related factors. Methods: This scoping review identifies instruments that are suitable for assessing emotional intelligence in the context of the lived and cultural experiences of individuals who are deaf or hard-of-hearing. A comprehensive search was conducted in April 2024 following the JBI methodology. Results: Out of 3091 articles, 21 studies were included. Two adapted methods were identified: the Meadow/Kendall Social–Emotional Assessment Inventory and ISEAR-D. Assessments supported by sign language revealed no significant differences in age or gender. Conclusions: The authors recommend further development of screening instruments that reflect the specific experiences of the population who are deaf or hard-of-hearing. Full article

Background/Objectives: Dementia, characterised by cognitive decline, significantly impacts language abilities. While the risk of dementia increases with age, it often manifests years before clinical diagnosis. Identifying early warning signs is crucial for timely intervention. Previous research has demonstrated that changes in language, such as reduced vocabulary diversity and simpler sentence structures, may be observed in individuals with dementia. This study investigates the potential of linguistic analysis to detect early signs of cognitive decline by examining the writing of Sir Terry Pratchett, a renowned author diagnosed with Posterior Cortical Atrophy (PCA), typically a form of dementia caused by Alzheimer’s disease. Methods: This study analysed 33 Discworld novels by Terry Pratchett, comparing linguistic features before and after a potential turning point identified through analysis of adjective type-token ratios (TTR). Results: A significant decrease in lexical diversity (TTR) was observed for nouns and adjectives in later works. Total wordcount increased, while lexical diversity decreased, suggesting a shift towards simpler language. This shift coincided with a decrease in adjective TTR below a defined threshold, occurring approximately ten years before Pratchett’s formal diagnosis. Conclusions: These findings suggest that subtle changes in linguistic patterns, such as decreased lexical diversity, may precede clinical diagnosis of dementia by a considerable margin. This research highlights the potential of linguistic analysis as a valuable tool for early detection of cognitive decline. Further research is needed to validate these findings in larger cohorts and explore the specific linguistic markers associated with different types of dementia. Full article