Deaf Research Articles

INTERAÇÕES SOCIAIS PROMOVIDAS EM ATIVIDADES EXPERIMENTAIS DE QUÍMICA EM PEQUENOS GRUPOS COM UMA PESSOA SURDA E OUVINTES

With the increasing number of deaf people in Brazilian schools, educational activities in the area of Science Education that contemplate them become increasingly necessary. Therefore, this work aims to analyze the potentialities and limits of a proposal for experimental activities in small groups for the teaching and learning processes of Chemistry in high school in a context with deaf and hearing people. The proposal was developed in a class of the 3rd year of high school in a public school and had as research subjects students from a group formed by a deaf student and three hearing students. Semi-structured interviews were conducted to analyze the initial student understandings about the deaf person and a sequence of experimental Chemistry activities to identify the social interactions promoted in the group and their possible relationships with the initial student understandings. The obtaining of qualitative information related to the sequence of experimental activities occurred through audio and video recordings. All qualitative information was submitted to the procedures of discursive textual analysis. The results indicate that the proposal was able to promote, especially, collaborative and tutorial interactions in the group. In addition, the initial student understandings about the deaf person may have influenced the social interactions promoted in the group.

Enhancing YOLOv3 with RNN Models: application to American Sign Language recognition for deaf individuals

As a natural language, sign language is a rich and expressive form of communication with properties similar to spoken languages. In this paper, we explore the application of transfer learning techniques to develop an intelligent system for recognizing American Sign Language. Instead of building a new deep convolutional neural network from scratch, we leveraged pre-trained models to capitalize on their advantages and reduce experimentation time. Specifically, we focused on YOLOv3 combined with advanced recurrent layers, including LSTM, GRU, and Bidirectional LSTM. The results were highly promising: YOLOv3 + Bidirectional LSTM achieved the highest accuracy, averaging over 94%, followed by YOLOv3 + LSTM at ~93%, and YOLOv3 + GRU at ~91%. These findings highlight the effectiveness of combining YOLOv3 with recurrent architectures for sign language recognition, demonstrating robust precision, recall, and F1 scores across models, with Bidirectional LSTM standing out as the top-performing configuration.

Sign Language to Text Conversion

Sign language is crucial for Deaf and non-verbal individuals to communicate, yet it remains unfamiliar to many, and interpreters are often scarce. To address this challenge, we developed a real-time system that recognizes fingerspelling in ASL using neural networks. Our process begins by filtering hand images to enhance key features. These enhanced images are then classified by a CNN. This method achieves an impressive 98.00% accuracy in recognizing all 26 letters of the alphabet, making it a highly effective tool for improving communication.

"Teledentistry" using a mobile app (Telesmile) to improve oral health among the visually impaired and hearing-impaired populations in Saudi Arabia: a randomized controlled study.

To assess the efficacy of a "teledentistry" method using a mobile app (Telesmile) in enhancing knowledge of oral health conditions and oral hygiene practices among the blind and deaf populations in Jazan Province in Saudi Arabia. A randomized parallel design controlled study was conducted among 50 blind and 50 deaf subjects between the ages of 12-18 years, randomly chosen from blind and deaf schools. The participants were selected based on the inclusion and exclusion criteria. An innovative teledentistry platform named Telesmile, a mobile application for the Apple iOS App Store and Google Play Store, was developed. Multimedia Arabic dental sign language oral hygiene instructional videos were created and uploaded in the Telesmile mobile application under the deaf category. Similarly, oral hygiene instructions were audio recorded by experts and uploaded under the blind category in the Telesmile mobile application. Group I of the blind (n = 25) and deaf participants (n = 25) received regular oral hygiene instructions while Group II of the blind (n = 25) and deaf (n = 25) participants received the Telesmile mobile application intervention. The knowledge of the participants pertaining to oral health and oral hygiene practices was evaluated using a close-ended questionnaire comprising 14 questions at the initial visit (T0). Training sessions were conducted for all participants and the Telesmile mobile application was distributed among the participants in Group II. After 4 weeks (T1), the knowledge of the participants regarding oral health and hygiene practice was re-evaluated and compared between each group. The chi-square test revealed that the marginal mean of the knowledge of the blind and deaf participants pertaining to oral health and oral hygiene practices was very poor at their initial visit (T0) and it significantly increased (p < 0.001) after 4 weeks (T1) of using the Telesmile mobile application. The Telesmile mobile application can significantly enhance oral hygiene knowledge among blind and deaf people. The audio technique was an effective tool to deliver oral health education which could result in improving the oral health status of blind participants. The video demonstrations were also effective in enhancing the oral health and oral hygiene knowledge of deaf individuals.

Video Remote Sign Language Interpreting in Health Communication for Deaf People: Protocol for a Randomized Controlled Trial.

The current standard of interpretation provision is not efficacious or not acceptable to Deaf patients who communicate using sign language. In-person or video relay interpretation (VRI) sign language interpretation is largely unavailable. There are no clear data on the availability of VRI or in-person interpretation. Given the limited number of available sign language interpreters and the cost, VRI may be more available than in-person. Existing evidence tends to focus on assessing personal preferences of Deaf users regarding interpretation and interpreters' preferences. Although respecting preferences is essential, there is a vacuum of knowledge on how the format of access to interpretation impacts the quality of communication between Deaf persons and health personnel. This study aims to look at the effectiveness of the VRI system in improving communication outcomes between Deaf patients and doctors versus the available standard of care of the usual communication tools, including informal interpretation, lip- or note-reading, and using their mobile phones to contact a formal or informal interpreter, for Deaf patients aged 18 years and older in Bogota, Colombia. This is a randomized controlled trial with a total sample size of 216 participants, divided into 2 groups: an intervention group, which receives a medical appointment using VRI, and a control group, which receives a medical appointment using standard communication. Both the Deaf participants and the health care professionals will be blinded to the allocation, as they will not know whether the appointment will involve VRI or standard communication until they arrive at the office. The primary outcome measure will be an assessment of communication using a Doctor-Patient Communication Scale. This scale was translated into Colombian Sign Language following a rigorous cultural adaptation and translation procedure. Furthermore, the database contains key clinical variables and recommendations provided by the doctor during a general medicine appointment. We will compute associations. Recruitment opened on August 24, 2023. As of July 2024, 180 participants had been enrolled. The intervention and data collection were finalized in October 2024. The findings of this study are expected to be submitted for publication in early 2025. This study will provide rigorous evidence regarding information and communications technology intervention in health care, addressing empirical challenges in using inclusive research designs in public health. In addition, effective VRI models that address the challenges faced by Deaf people will be tested, implemented, and maintained in low- and middle-income countries. A disability-inclusive evaluative tool for quality communication mediated by VRI in health care is also tested. Ultimately, this will lead to evidence-based recommendations for implementing the Convention on the Rights of Persons with Disabilities (CRPD) in mobile health contexts. ClinicalTrials.gov NCT05966623; https://clinicaltrials.gov/study/NCT05966623. DERR1-10.2196/64590.

Recognizing Indonesian sign language (Bisindo) gesture in complex backgrounds

Sign language, particularly Indonesian sign language (Bisindo), is vital for deaf individuals, but learning it is challenging. This study aims to develop an automated Bisindo recognition system suitable for diverse backgrounds. Previous research focused on greenscreen backgrounds and struggled with natural or complex backgrounds. To address this problem, the study proposes using Faster region-based convolutional neural networks (RCNN) and YOLOv5 for hand and face detection, MobileNetV2 for feature extraction, and long short-term memory (LSTM) for classification. The system is also designed to focus on computational efficiency. YOLOv5 model achieves the best result with a sentence accuracy (SAcc) of 49.29% and a word error rate (WER) of 16.42%, with a computational time of 0.0188 seconds, surpassing the baseline model. Additionally, the system achieved a SacreBLEU score of 67.77%, demonstrating its effectiveness in Bisindo recognition across various backgrounds. This research improves accessibility for deaf individuals by advancing automated sign language recognition technology.

Sign Language Translator via Smartphone Image Analysis using Convolutional Neural Network

This study presents the design and implementation of a smartphone-based image processing system aimed at translating sign language gestures into text in real-time. The primary objective was to create a platform that enhances communication between deaf individuals and non-sign language users through the accurate recognition of sign language gestures. Using Kotlin programming and MediaPipe, the system captures and processes gestures, converting them into readable text. The results demonstrated that the system is capable of recognizing and translating various sign language gestures with a high degree of accuracy and efficiency. The successful deployment of this system highlights its potential to break down communication barriers and offers a foundation for future improvements, including expanded sign language support and performance optimization for real-world applications.

A flexible wearable sensor based on improving the piezoelectric layer performance of sandwich structures with micro-/mesopores for communication with the deaf-mute

Layered H-UiO-66@IL composites with both intraparticle micropores, interparticle mesopores, and multiple active sites were prepared. A key aspect of the technique was the addition of deionized water during solvothermal synthesis, which rapidly nucleated layered nanoparticles. A multifunctional, flexible, and stable polyacrylonitrile (PAN)-based membrane was successfully constructed by incorporating H-UiO-66 nanoparticles, modified by ionic liquid (1-allyl-3-butylimidazole tetrafluoroborate), into polymers with macromolecular chains under mild, controlled conditions. The resulting film exhibited excellent dielectric, ferroelectric, and mechanical properties due to the multilayer fiber design. Furthermore, the PAN matrix showed a higher content (97.41 %) of planar zigzag conformations, enhancing the piezoelectric properties. The composite film demonstrated ultra-high sensitivity (10.98 V/N) and an ultra-low detection limit of 3.5 × 10⁻⁴ N. In addition, the film passed 1,800-cycle stability tests and maintained its initial output value across various environmental conditions. This flexible piezoelectric sensor shows significant potential for aiding deaf and mute individuals in sign language or breathing communication.

Optimasi Deteksi Gerak Bahasa Isyarat dan Ekpresi Wajah Real Time Dengan Metode Random Forest

Sign language is the primary means of communication for deaf individuals, one of the alternative languages used by people with disabilities, and it has evolved from the deaf community. Sign language has many variations, making it something unfamiliar and difficult to interpret for some hearing or uninitiated people. This research aims to develop a real-time sign language motion and facial expression detection system using the Random Forest method. The main challenge in this detection is the complexity and variation of the movements and facial expressions. In this study, MediaPipe is used to extract features from video input, which are then analyzed using the Random Forest algorithm for classification. In this research, the model's evaluation results use a confusion matrix with testing scenarios based on the division of training and testing data. From the model evaluation results, an accuracy of 99% was achieved. This research is expected to help deaf individuals communicate with hearing people, thereby reducing social gaps.

Mental health services for the deaf: an exploratory study of the aetiology, sources of information, and access to mental health services among deaf persons in Ghana

BackgroundThe global burden of mental health disorders is on the increase, which has contributed to discussions on mitigation strategies. While mental health discourses in respect of access to services are still ongoing, there is limited focus on vulnerable groups. Deaf persons are at risk of exclusion from health services due to their unique modes of communication. In order to advocate for the inclusion of deaf persons in mental health services, there is a need for a study eliciting information on their knowledge about mental health and accessibility to services.MethodThe study was guided by a mixed-methods design and a two-phase data collection. In phase one, a questionnaire was distributed to 284 deaf persons to gather information on their knowledge of mental health conditions, causes, sources of information, and accessibility of services. Frequencies were used to report the trends identified in the data. Following this, an interview guide was designed based on the trends identified in the first phase to develop an in-depth insight into the experiences of deaf persons (n = 40) in respect of awareness and accessibility to mental health services.ResultsThe results showed convergences and divergence between the qualitative and quantitative data. For instance, they were convergences between both datasets relative to knowledge on and causes of mental health conditions.ConclusionThe study highlights the need for health policymakers to leverage the information gathered on the study participants’ knowledge to develop appropriate mental health training programmes for deaf persons.

Homesign Research, Gesture Studies, and Sign Language Linguistics: The Bigger Picture of Homesign and Homesigners.

Studies of homesigns have shed light on the human capacity for language and on the challenging problem of language acquisition. The study of homesign has evolved from a perspective grounded in gesture studies and child development to include sign language linguistics and the role of homesigns in language emergence at the community level. One overarching finding is that homesigns more closely resemble sign languages used by linguistic communities than they resemble the gestures produced by hearing people along with spoken language. Homesigns may not exhibit all of the linguistic properties of community languages, but the properties they do exhibit are language properties, and for the people who use them, homesigns are their language. Further, the linguistic structures in homesigns are innovated by the deaf people who use them and are imperfectly learned by their hearing communication partners. I close with a call to action: We cannot celebrate discoveries about the mind made possible by studies of homesigns and emerging languages while ignoring the pervasiveness of language deprivation among deaf people, and the relative lack of deaf participation in science, even in studies of sign languages. While the scientific community learns much from studying homesigns and sign languages, we also have a responsibility to work toward ensuring that every deaf person has access to language, communication, and education.

UTILIZING CONVOLUTIONAL NEURAL NETWORKS TO COMPREHEND SIGN LANGUAGE AND RECOGNIZE EMOTIONS

The inability to communicate verbally is widely acknowledged as a significant disability. The primary objective of this research is to create a practical system aimed at individuals with hearing impairments, particularly those who depend on sign language as their primary means of communication. This system aims to enable deaf individuals to express themselves, communicate effectively and facilitate understanding of their language which would otherwise be challenging since most people are unfamiliar with sign language. By employing human gesture interpretation and motion capture, this technology can facilitate the translation of sign language into spoken language and vice versa. Despite the existence of various methods to convert sign language into voice, none of them currently provide an entirely intuitive user interface. Our objective is to create a system that not only translates sign language but also integrates a natural user interface, thus enhancing accessibility for individuals who are blind or have visual impairments. This system will achieve this by recognizing facial expressions and effectively conveying emotions behind words assisting visually impaired individuals in expressing themselves more effectively. Hence, in this project, we tentatively aim to build a system that can ease the lives of blind, deaf and dumb people to some extent. Normal communication like normal people do might never be possible for differently abled people but through our project, we try to provide them with a tool that can help them experience normalcy while communicating with normal people.

Argument ordering in simple sentences is affected by age of first language acquisition: Evidence from late first language signers of ASL.

Research on the language acquisition of deaf individuals who are exposed to accessible linguistic input at a variety of ages has provided evidence for a sensitive period of first language acquisition. Recent studies have shown that deaf individuals who first learn language after early childhood, late first-language learners (LL1), do not comprehend reversible Subject-Verb-Object (SVO) sentences. The present study analyzed 478 signed productions elicited with pictures depicting simple events with one or two arguments by 28 signers. The argument order patterns of native signers converged with one another and the word order patterns of American Sign Language (ASL). By contrast, the ordering patterns of the LL1 signers did not converge with one another or with the patterns of the native signers. This indicates that early childhood is a period of heightened sensitivity to basic word order and may help explain why complex structures are difficult for LL1 signers to learn.

Advanced Hybrid Neural Networks for Accurate Recognition of the Extended Alphabet and Dynamic Signs in Mexican Sign Language (MSL)

The Mexican deaf community primarily uses Mexican Sign Language (MSL) for communication, but significant barriers arise when interacting with hearing individuals unfamiliar with the language. Learning MSL requires a substantial commitment of at least 18 months, which is often impractical for many hearing people. To address this gap, we present an MSL-to-Spanish translation system that facilitates communication through a spelling-based approach, enabling deaf individuals to convey any idea while simplifying the AI’s task by limiting the number of signs to be recognized. Unlike previous systems that focus exclusively on static signs for individual letters, our solution incorporates dynamic signs, such as “k”, “rr”, and “ll”, to better capture the nuances of MSL and enhance expressiveness. The proposed Hybrid Neural Network-based algorithm integrates these dynamic elements effectively, achieving an F1 score of 90.91%, precision of 91.25%, recall of 91.05%, and accuracy of 91.09% in the extended alphabet classification. These results demonstrate the system’s potential to improve accessibility and inclusivity for the Mexican deaf community.

The Charactertistics and neural mechanisms of trait and state empathy in deaf individuals

Empathy deficiencies are prevalent among deaf individuals. It has yet to be determined whether they exhibit deficiencies in both trait empathy and state empathy, along with the effect of top-down attention. Here, the current study employed the IRI-C scale and physiological pain empathy tasks (A-P task and A-N task) to explore the temporal dynamics of neural activities when deaf individuals were processing second-hand painful/non-painful stimuli. For trait empathy, we found that deaf individuals have deficiencies in both emotional and cognitive empathy compared to their hearing counterparts. For state empathy, we found that deaf individuals showed stronger automatic emotional empathy responses and paid more cognitive evaluation resources. Moreover, the differential processing of empathy between deaf individuals and hearing individuals towards others’ pain could be regulated by top-down attention, which occurs both in the early and late processing stages of pain empathy.

Sign language recognition using convolutional neural network

: Sign language detection plays a vital role in enhancing accessibility, communication, and inclusion for individuals who are deaf or hard of hearing. It is an essential tool that facilitates smooth communication in various environments, such as schools, workplaces, healthcare settings, and daily interactions. By accurately identifying and interpreting sign language gestures, this technology helps bridge communication barriers between sign language users and those unfamiliar with it, ensuring equal access to information and services. In education, this technology supports language learning, literacy, and academic achievement for deaf students. In healthcare, reliable sign language detection ensures that medical information and consultations are conveyed clearly, improving care quality for deaf patients. In the workplace, it promotes inclusivity by enabling effective communication between deaf employees, their colleagues, and clients, fostering equal opportunities and professional growth. Additionally, during emergencies, this technology can save lives by facilitating swift and precise communication between emergency responders and deaf individuals. When incorporated into assistive technologies, sign language detection enables deaf individuals to independently handle everyday tasks, such as accessing digital content, using smart devices, and engaging in online interactions.

Translate Arabic Text to Arabic Gloss for Sign Language

Arabic Sign Language (ArSL) is a language used by the deaf community across Arab countries, but the lack of familiarity with ArSL among the hearing population often leads to social isolation for deaf individuals. The structural differences between ArSL and spoken Arabic pose significant challenges for machine translation. In this study, we enhance Arabic to ArSL gloss translation by employing data augmentation techniques, expanding the dataset from 600 to over 23,328 samples using sequence-to-sequence transformer models. Our approach achieved a substantial performance improvement, increasing the BLEU score from 11.1% in the baseline model to 52.72% on original test set. The best model achieved a BLEU score of 85.17% on augmented data test, underscoring the effectiveness of data augmentation in enhancing ArSL translation quality.

SignifAI: French sign language translation based on deep learning and large language models

In this project, we propose SignifAI which is an AI-powered software that translates French Sign Language into spoken French. The goal of SignifAI is to remove the language barrier that separates the deaf and hearing communities. The translation process proves to be a major challenge for existing methods, as most of them rely on traditional Natural Language Processing (NLP) methods which solve the task in a similar way as spoken languages (e.g., paying more attention to the logics and reasoning). The drastic syntactical difference between sign and spoken languages, however, makes such approaches not as effective and efficient. In SignifAI, we propose to leverage a combination of deep learning models for sign gesture recognition and large language models (LLM) for sentence generation from recognized words. The former allows for precise detection of individual words, while the latter takes the recognized words as inputs and returns a fluently reformulated translated sentence. With extremely limited data available for French sign language, we created our own enhanced dataset through synthetically augmenting existing videos. Utilizing the SlowFast model for this task, we have achieved a maximum test accuracy of 98.9%, and a fluid translation process after implementing ChatGPTs API. The potential applications of SignifAI range from aiding communication between the deaf and the hearing, to helping the deaf place phone calls in numerical services. Ultimately, SignifAI strives to improve all aspects of a deaf persons life, and compensates for their speaking disabilities.

Indexical deprivation: The dominant link between cochlear implants and global English among Taiwanese deaf individuals

AbstractThis paper develops the concept of “indexical deprivation” from the experiences of English learning in relation to cochlear implant use among Taiwanese deaf adults. Based on the framework of language ideological assemblage, this paper traces how institutional discourses and practices at different levels contribute to the indexicalization between cochlear implants and elevated proficiency in English as a global language. By examining the top‐down discourses and bottom‐up narratives of two Taiwanese deaf women, the study demonstrates how enhanced English proficiency has been linked to cochlear implants and how individuals are deprived of the capacity to recognize alternative links. This paper highlights how global English has promoted the status of cochlear implants in a sociolinguistic context where English is spoken as a foreign language and increasingly gains prominence at multiple societal levels.

LÍNGUA BRASILEIRA DE SINAIS: BREVE HISTÓRICO DOS ASPECTOS EDUCACIONAIS DOS SURDOS

This article aims to present a compendium of the evolutionary history of Brazilian Sign Language (Libras) and its reflections on the deaf community, particularly concerning education for all. Schooling must be ensured for everyone, and therefore, addressing any disparities caused by specific needs is crucial. This dynamism reflects the shared responsibility of public and private agencies within legislative and educational contexts to provide specific training related to the language and prepare the environment for promoting teaching and learning. The method used involved exploratory bibliographic research in scientific articles and books, with filters for the central theme of this work. The results reveal a concerning state of involvement and interaction of public policies and effective actions for the integration and inclusion of deaf individuals in social and educational contexts, highlighting the challenge for more in-depth research on the topic to promote solutions and address the social disparities faced by these individuals.