American Sign Language Recognition and Translation Using Perception Neuron Wearable Inertial Motion Capture System

Sign language is designed as a natural communication method to convey messages among the deaf community. In the study of sign language recognition through wearable sensors, the data sources are limited, and the data acquisition process is complex. This research aims to collect an American sign language dataset with a wearable inertial motion capture system and realize the recognition and end-to-end translation of sign language sentences with deep learning models. In this work, a dataset consisting of 300 commonly used sentences is gathered from 3 volunteers. In the design of the recognition network, the model mainly consists of three layers: convolutional neural network, bi-directional long short-term memory, and connectionist temporal classification. The model achieves accuracy rates of 99.07% in word-level evaluation and 97.34% in sentence-level evaluation. In the design of the translation network, the encoder-decoder structured model is mainly based on long short-term memory with global attention. The word error rate of end-to-end translation is 16.63%. The proposed method has the potential to recognize more sign language sentences with reliable inertial data from the device.

Impoverished language in early childhood affects the development of complex sentence structure

The hypothesis that impoverished language experience affects complex sentence structure development around the end of early childhood was tested using a fully randomized, sentence-to-picture matching study in American Sign Language (ASL). The participants were ASL signers who had impoverished or typical access to language in early childhood. Deaf signers whose access to language was highly impoverished in early childhood (N = 11) primarily comprehended structures consisting of a single verb and argument (Subject or Object), agreeing verbs, and the spatial relation or path of semantic classifiers. They showed difficulty comprehending more complex sentence structures involving dual lexical arguments or multiple verbs. As predicted, participants with typical language access in early childhood, deaf native signers (N = 17) or hearing second-language learners (N = 10), comprehended the range of 12 ASL sentence structures, independent of the subjective iconicity or frequency of the stimulus lexical items, or length of ASL experience and performance on non-verbal cognitive tasks. The results show that language experience in early childhood is necessary for the development of complex syntax. RESEARCH HIGHLIGHTS: Previous research with deaf signers suggests an inflection point around the end of early childhood for sentence structure development. Deaf signers who experienced impoverished language until the age of 9 or older comprehend several basic sentence structures but few complex structures. Language experience in early childhood is necessary for the development of complex sentence structure.

Deep Learning Technology to Recognize American Sign Language Alphabet

Historically, individuals with hearing impairments have faced neglect, lacking the necessary tools to facilitate effective communication. However, advancements in modern technology have paved the way for the development of various tools and software aimed at improving the quality of life for hearing-disabled individuals. This research paper presents a comprehensive study employing five distinct deep learning models to recognize hand gestures for the American Sign Language (ASL) alphabet. The primary objective of this study was to leverage contemporary technology to bridge the communication gap between hearing-impaired individuals and individuals with no hearing impairment. The models utilized in this research include AlexNet, ConvNeXt, EfficientNet, ResNet-50, and VisionTransformer were trained and tested using an extensive dataset comprising over 87,000 images of the ASL alphabet hand gestures. Numerous experiments were conducted, involving modifications to the architectural design parameters of the models to obtain maximum recognition accuracy. The experimental results of our study revealed that ResNet-50 achieved an exceptional accuracy rate of 99.98%, the highest among all models. EfficientNet attained an accuracy rate of 99.95%, ConvNeXt achieved 99.51% accuracy, AlexNet attained 99.50% accuracy, while VisionTransformer yielded the lowest accuracy of 88.59%.

New combined DT-CWT and HOG descriptor for static and dynamic hand gesture recognition

In recent years, researchers have been focusing on developing Human-Computer Interfaces that are fast, intuitive, and allow direct interaction with the computing environment. One of the most natural ways of communication is hand gestures. In this context, many systems were developed to recognize hand gestures using numerous vision-based techniques, these systems are highly affected by acquisition constraints, such as resolution, noise, lighting condition, hand shape, and pose. To enhance the performance under such constraints, we propose a static and dynamic hand gesture recognition system, which utilizes the Dual-Tree Complex Wavelet Transform to produce an approximation image characterized by less noise and redundancy. Subsequently, the Histogram of Oriented Gradients is applied to the resulting image to extract relevant information and produce a compact features vector. For classification, we compare the performance of three Artificial Neural Networks, namely, MLP, PNN, and RBNN. Random Decision Forest and SVM classifiers are also used to ameliorate the efficiency of our system. Experimental evaluation is performed on four datasets composed of alphabet signs and dynamic gestures. The obtained results demonstrate the efficiency of the combined features, for which the achieved recognition rates were comparable to the state-of-the-art.

Unique N170 signatures to words and faces in deaf ASL signers reflect experience-specific adaptations during early visual processing

Previous studies with deaf adults reported reduced N170 waveform asymmetry to visual words, a finding attributed to reduced phonological mapping in left-hemisphere temporal regions compared to hearing adults. An open question remains whether this pattern indeed results from reduced phonological processing or from general neurobiological adaptations in visual processing of deaf individuals. Deaf ASL signers and hearing nonsigners performed a same-different discrimination task with visually presented words, faces, or cars, while scalp EEG time-locked to the onset of the first item in each pair was recorded. For word recognition, the typical left-lateralized N170 in hearing participants and reduced left-sided asymmetry in deaf participants were replicated. The groups did not differ on word discrimination but better orthographic skill was associated with larger N170 in the right hemisphere only for deaf participants. Face recognition was characterized by unique N170 signatures for both groups, and deaf individuals exhibited superior face discrimination performance. Laterality or discrimination performance effects did not generalize to the N170 responses to cars, confirming that deaf signers are not inherently less lateralized in their electrophysiological responses to words and critically, giving support to the phonological mapping hypothesis. P1 was attenuated for deaf participants compared to the hearing, but in both groups, P1 selectively discriminated between highly learned familiar objects - words and faces versus less familiar objects - cars. The distinct electrophysiological signatures to words and faces reflected experience-driven adaptations to words and faces that do not generalize to object recognition.

The validity of the test of memory malingering (TOMM) with deaf individuals

OBJECTIVE

Administration of performance validity tests (PVT) during neuropsychological assessments is standard practice, with the Test of Memory Malingering (TOMM) being a commonly used measure. The TOMM has been well validated in hearing populations with various medical and psychiatric backgrounds. A major gap in the literature is the use of the TOMM amongst culturally Deaf individuals who use American Sign Language (ASL) as their first and preferred language. The purpose of this study was to explore the use of the TOMM with this population to determine if there may be differences related to the use of semantic knowledge and recall using signs rather than spoken phonemes.

METHOD

This study recruited 30 culturally Deaf, community-dwelling adults, who self-reported that they were not involved in litigation ordisability claims. In addition to the TOMM, participants were screened for cognitive ability using non-verbal components of the Wechsler Abbreviated Scale of Intelligence, Second Edition (WASI-II) and the Mini Mental State Examination: ASL Version (MMSE:ASL).

RESULTS

Nonverbal intelligence for this sample was within the average range of ability. No participants scored lower than the standard cut-off score for Trial 2 or the Retention Trial on the TOMM (≤44 raw score to indicate invalid responding). Trial 1 performances ranged from 44 to 50, Trial 2 performances ranged from 49 to 50, and Retention performances ranged from 49 to 50.

CONCLUSION

These results support the use of the same standard cut-off scores established for hearing individuals in culturally Deaf individuals who use ASL.

Young Deaf Adults' Knowledge of Human Papillomavirus and Human Papillomavirus Vaccine's Effectiveness in Preventing Cervical, Anal, Penile, and Oral Cancer

STUDY OBJECTIVE

To describe knowledge and risk perception of human papillomavirus (HPV) among deaf adults who use American sign language (ASL) comparison with hearing adults in the United States.

DESIGN

Secondary HPV knowledge data for the deaf subset sample were drawn from the Health Information National Trends survey in ASL that was administered between 2015 and 2018. HPV knowledge data for the hearing subset sample were drawn from cycle 5 of the Health Information National Trends survey in English that was administered in 2017.

SETTING

Surveys are a nationally based survey of deaf ASL users in the United States and a nationally based survey of hearing non-ASL users in the United States.

PARTICIPANTS

The age of the deaf and hearing subset samples was determined on the basis of catchup vaccine eligibility criteria as outlined by the Centers for Disease Control and Prevention that recommends catchup vaccination in women, men who have sex with men, immunocompromised individuals, and those who identify as transgender.

INTERVENTIONS AND MAIN OUTCOME MEASURES

We examined HPV, HPV vaccine, and HPV-related cancer knowledge in deaf and hearing subsets.

RESULTS

Our sample consisted of 235 deaf and 115 hearing adults aged 18-26 years. Of the deaf participants 58% (136/235) reported knowledge of HPV compared with 84% (97/115) of hearing participants (P < .001). Hearing participants showed higher accuracy in risk perception of HPV relation to cervical cancer compared with deaf participants (P < .001). Hearing participants were more likely to have heard of the HPV vaccine as well as believe it is successful in preventing cervical cancer compared with deaf participants (P < .001).

CONCLUSION

Deaf ASL users are less likely to have knowledge of HPV, virus-related cancer risk, and preventative vaccination compared with hearing peers.

Deaf Families' Unique Experiences and Obstacles

This article focuses on deaf children of deaf parents who grew up using American Sign Language (ASL) in deaf culture. Deaf children of deaf parents described their unique experiences of struggling with obstacles, including quality of education, low expectations from professionals, unwanted sympathy, mental health therapists' lack of cultural competency, and not being asked for valuable perspectives or advice. The advice from deaf children of deaf parents is included in the article. By bringing greater attention to this population, mental health, school, and other professionals can increase their awareness of deaf families' unique needs in their work environment.

Forensic Evaluation of Deaf Individuals: Challenges and Strategies

Forensic evaluation of deaf individuals presents unique challenges due to many examinees' fund of information deficits, potential for language deprivation, and examiners' frequent lack of creativity regarding communication methods. This article describes challenges most frequently encountered in competency to stand trial and criminal responsibility evaluations and offers strategies for overcoming them. The value of employing multiple communication methods, especially the use of illustrations, is emphasized. Suggestions also are offered regarding preparing evaluation reports and effectively communicating "key deaf fundamentals" to legal personnel. Encouragement is offered for qualified, sign-fluent professionals to engage in forensic work.

Synesthesia for manual alphabet letters and numeral signs in second-language users of signed languages

Many synesthetes experience colors when viewing letters or digits. We document, for the first time, an analogous phenomenon among users of signed languages who showed color synesthesia for fingerspelled letters and signed numerals. Four synesthetes experienced colors when they viewed manual letters and numerals (in two cases, colors were subjectively projected on to the hands). There was a correspondence between the colors experienced for written graphemes and their manual counterparts, suggesting that the development of these two types of synesthesia is interdependent despite the fact that these systems are superficially distinct and rely on different perceptual recognition mechanisms in the brain.

Functional connectivity in task-negative network of the Deaf: effects of sign language experience

Prior studies investigating cortical processing in Deaf signers suggest that life-long experience with sign language and/or auditory deprivation may alter the brain’s anatomical structure and the function of brain regions typically recruited for auditory processing (Emmorey et al., 2010; Pénicaud et al., 2013 inter alia). We report the first investigation of the task-negative network in Deaf signers and its functional connectivity—the temporal correlations among spatially remote neurophysiological events. We show that Deaf signers manifest increased functional connectivity between posterior cingulate/precuneus and left medial temporal gyrus (MTG), but also inferior parietal lobe and medial temporal gyrus in the right hemisphere- areas that have been found to show functional recruitment specifically during sign language processing. These findings suggest that the organization of the brain at the level of inter-network connectivity is likely affected by experience with processing visual language, although sensory deprivation could be another source of the difference. We hypothesize that connectivity alterations in the task negative network reflect predictive/automatized processing of the visual signal.

Cross-linguistic differences in the neural representation of human language: evidence from users of signed languages

Studies of deaf individuals who are users of signed languages have provided profound insight into the neural representation of human language. Case studies of deaf signers who have incurred left- and right-hemisphere damage have shown that left-hemisphere resources are a necessary component of sign language processing. These data suggest that, despite frank differences in the input and output modality of language, core left perisylvian regions universally serve linguistic function. Neuroimaging studies of deaf signers have generally provided support for this claim. However, more fine-tuned studies of linguistic processing in deaf signers are beginning to show evidence of important differences in the representation of signed and spoken languages. In this paper, we provide a critical review of this literature and present compelling evidence for language-specific cortical representations in deaf signers. These data lend support to the claim that the neural representation of language may show substantive cross-linguistic differences. We discuss the theoretical implications of these findings with respect to an emerging understanding of the neurobiology of language.