Sign Language Words Research Articles

АББРЕВИАТУРА В ГРАММАТИКЕ ГОВОРЯЩЕГО: ЭКСПЕРИМЕНТАЛЬНОЕ ИССЛЕДОВАНИЕ

The article presents the results of a directed associative experiment carried out with high school students of secondary schools. The purpose of the article is to reveal the relationship between the structural and semantic features of the utterance and the strategies of the respondents’ choice of a linguistic sign (word/abbreviation) in the context of a directed associative experiment. The analysis of the experimental material made it possible to draw conclusions about the peculiarities of using the initial abbreviation as an associate; about the possibility of the abbreviation of stable and individual, situational associative links; about the strategies for choosing a linguistic sign (words, abbreviations, phrases) depending on the semantics of the reference word and the type of grammatical structure of the experimental sentence; on the consolidation of initial abbreviations in the linguistic consciousness of native speakers of the Russian language, which is associated with the strengthening of the law of economy of linguistic means in modern speech communication.

ВАЛЕНТНІСНІ ВЛАСТИВОСТІ ПРИСЛІВНИКОВИХ ПРЕДИКАТІВ ЯКОСТІ ТА ПРЕДИКАТІВ СТАНУ

An adverb is the most peripheral part-of-speech class of attributive words in terms of its semantic and grammatical characteristics. The sign of an adverb is a reflection of the syntactic relations of sign words – attributive, circumstantial and others. An adverbial sign appears as a static sign of a predicate or an attribute of an object. Adverbs that perform the function of an adverbial compound predicate in a two-member sentence and an adverbial compound of a principal part of a one-member sentence are formal-grammatical correlates of state predicates; prominent among them are the predicates of the qualitative-evaluative state and the predicates of the state of the environment, the external state of a certain spatial object, the emotional-mental, physical and physiological state of a being, etc. Adverbs, like other classes of attributive words, have a category of semantic-syntactic valence, but it has a transpositional character, because they acquire it in connection with the transposition into formal-syntactic positions of the verb – adverbial compound predicate in two-member sentence and an adverbial compound of a principal part in a simple sentence. The defining feature of the valence of adverbial predicates is smallness, because quality predicates and adverbial predicates of state, which correlate with the adverbial compound predicate of a two-member sentence and an adverbial compound of a principal part in a simple sentence, are monovalent. In addition to obligatory subject valence, some predicates of qualitative and modal semantics may have optional and some even obligatory object valence. Characteristically, subjective valence correlates with a subject, a typically expressed by non-predicate noun with the meaning of an object or a being, or substantivized by demonstrative pronoun adjectives this, that, only in the formal-syntactic structure of an elementary two-member sentence with an adverbial compound predicate. This valence is more often represented by the infinitive form or the predicate noun in a non-elementary two-member sentence.

Teaching American Sign Language in Mixed Reality

This paper presents a holistic system to scale up the teaching and learning of vocabulary words of American Sign Language (ASL). The system leverages the most recent mixed-reality technology to allow the user to perceive her own hands in an immersive learning environment with first- and third-person views for motion demonstration and practice. Precise motion sensing is used to record and evaluate motion, providing real-time feedback tailored to the specific learner. As part of this evaluation, learner motions are matched to features derived from the Hamburg Notation System (HNS) developed by sign-language linguists. We develop a prototype to evaluate the efficacy of mixed-reality-based interactive motion teaching. Results with 60 participants show a statistically significant improvement in learning ASL signs when using our system, in comparison to traditional desktop-based, non-interactive learning. We expect this approach to ultimately allow teaching and guided practice of thousands of signs.

Towards Domain-independent Complex and Fine-grained Gesture Recognition with RFID

Gesture recognition plays a fundamental role in emerging Human-Computer Interaction (HCI) paradigms. Recent advances in wireless sensing show promise for device-free and pervasive gesture recognition. Among them, RFID has gained much attention given its low-cost, light-weight and pervasiveness, but pioneer studies on RFID sensing still suffer two major problems when it comes to gesture recognition. The first is they are only evaluated on simple whole-body activities, rather than complex and fine-grained hand gestures. The second is they can not effectively work without retraining in new domains, i.e. new users or environments. To tackle these problems, in this paper, we propose RFree-GR, a domain-independent RFID system for complex and fine-grained gesture recognition. First of all, we exploit signals from the multi-tag array to profile the sophisticated spatio-temporal changes of hand gestures. Then, we elaborate a Multimodal Convolutional Neural Network (MCNN) to aggregate information across signals and abstract complex spatio-temporal patterns. Furthermore, we introduce an adversarial model to our deep learning architecture to remove domain-specific information while retaining information relevant to gesture recognition. We extensively evaluate RFree-GR on 16 commonly used American Sign Language (ASL) words. The average accuracy for new users and environments (new setup and new position) are $89.03%$, $90.21%$ and $88.38%$, respectively, significantly outperforming existing RFID based solutions, which demonstrates the superior effectiveness and generalizability of RFree-GR.

Семиотика «пандемического» дискурса: «новояз» эпохи карантина

The article examines the specifics of semiosis, which results in signs for the nomination of new realities in the context of a coronavirus pandemic. The study shows that “Newspeak” of the quarantine era is formed during the work process of two main mechanisms: the extension of the already existing meanings of word signs in the language (war, front line, enemy, embrasure, paranoia, bacchanalia) and production of words according to standard derivational models, activating in the minds of native speakers in case of need (covidnyi, covidarii, dokarantinnyi, poslekarantinnyi, karantinit’). Using these mechanisms, native speakers act in accordance with the principle of language economy, relying on their existing knowledge and stereotypes of language production to learn new experiences. The third way for new words to appear is through borrowing, which takes a less significant place in creating “Newspeak” of the pandemic era (lockdown, sanitizer). The “pandemic” discourse is characterized by such connotative signifiers as negative evaluation and emotionality, globalization of perception, uncontrollability, and unpredictability. They determine a person's choice to connect language signs and new objects during semiosis.

Stemming Algorithm for Indonesian Signaling Systems (SIBI)

The Indonesian Language Sign System (SIBI) is a medium used by deaf people to communicate with the wider community. SIBI is Indonesian that is presented by hand. The sentence structure (morphology) of SIBI is the same as the Indonesian language, SIBI also recognizes the prefix, principal and suffix sign word. This research discusses how to make stemming for SIBI, the algorithm used for stemming is Nazief Adiri. Stemming for SIBI separates input sentences, words through the Text Processing process. Then the word in Stemming so that it can be separated into prefix, main, and suffix words. After stemming, the words obtained in indexing can find the right SIBI, by using ID. Good stemming must pay attention to Indonesian Morphology. The number of words used for this stemming trial is 50 words. By using the Confusion Matrix method found 0.94% accuracy, 93% recall, and 84% precision.

Hand gestures for emergency situations: A video dataset based on words from Indian sign language.

Automatic sign language recognition provides better services to the deaf as it avoids the existing communication gap between them and the rest of the society. Hand gestures, the primary mode of sign language communication, plays a key role in improving sign language recognition. This article presents a video dataset of the hand gestures of Indian sign language (ISL) words used in emergency situations. The videos of eight ISL words have been collected from 26 individuals (including 12 males and 14 females) in the age group of 22 to 26 years with two samples from each individual in an indoor environment with normal lighting conditions. Such a video dataset is highly needed for automatic recognition of emergency situations from the sign language for the benefit of the deaf. The dataset is useful for the researchers working on vision based sign language recognition (SLR) as well as hand gesture recognition (HGR). Moreover, support vector machine based classification and deep learning based classification of the emergency gestures has been carried out and the base classification performance shows that the database can be used as a benchmarking dataset for developing novel and improved techniques for recognizing the hand gestures of emergency words in Indian sign language.

HISTORY OF STUDYING THE PROCESS OF FUSED WRITING WORDS IN KAZAKH LINGUISTICS

The article considers one of the most difficult problems in the spelling of the In the spelling of the Kazakh language is the search for reasons for joint or separate spelling of words. According to this, Kazakh linguistics was conducted a review research, and studied the recognition of a joint word in morphology, semasiology, and spelling. Beginning with the research of A. Baitursynov and K. Zhubanov, a review of the works of scientists who became the subject of a special study of this topic was conducted. Some of the authors’conclusions are distributed and differentiated. Phonetic reasons and signs of merging complex words: Professor K. Zhubanov, semantic sign defended his thesis on this topic. As noted by academician R. Syzdyk and professors N. Uali, B. Kaliev for the first time studied and published in scientific circulation, and in particular, in the joint construction used the connotation-denotation theory of profesor N. Uali, on this basis they made a scientific conclusion

Key Word Signing Has Higher Iconicity Than Sign Language.

Purpose Key word signing (KWS) entails using manual signs to support the natural speech of individuals with normal hearing and who have communication difficulties. While manual signs from the local sign language may be used for this purpose, some KWS systems have opted for a distinct KWS lexicon. Distinct KWS lexicon typically aims for higher sign iconicity or recognizability to make the lexicon more accessible for individuals with intellectual disabilities. We sought to determine if, in the Belgian Dutch context, signs from such a distinct KWS lexicon (Spreken Met Ondersteuning van Gebaren [Speaking With Support of Signs; SMOG]) were indeed more iconic than their Flemish Sign Language (FSL) counterparts. Method Participants were 224 adults with typical development who had no signing experience. They rated the resemblance between a FSL sign and its meaning. Raw data on the iconicity of SMOG from a previous study were used. Translucency was statistically and qualitatively compared between the SMOG lexicon and their FSL counterparts. Results SMOG had an overall higher translucency than FSL and contained a higher number of iconic signs. Conclusion This finding may support the value of a separate sign lexicon over using sign language signs. Nevertheless, other aspects, such as wide availability and inclusion, need to be considered.

Semantic Boundary Detection With Reinforcement Learning for Continuous Sign Language Recognition

Sign language recognition (SLR) is a significant and promising technique to facilitate the communication for the hearing-impaired people. In this paper, we are dedicated to weakly supervised continuous SLR, where for each sign video, there are only ordered gloss labels without temporal boundary along frames. To explicitly align video frames to the sign words in a sign video, we propose a novel semantic boundary detection method based on reinforcement learning for accurate continuous SLR. In our approach, we first propose a multi-scale perception scheme to learn discriminative representation for video clips. Then, we formulate the semantic boundary detection as a reinforcement learning problem. We define the state as the feature representation of a video segment, and the action as the determination of the semantic boundary’s location. The reward is computed by the quantitative performance metric between the prediction sentence and the ground truth sentence. The policy network is trained with a policy gradient algorithm. Extensive experiments are conducted on CSL Split II and RWTH-PHOENIX-Weather 2014 datasets, and the results demonstrate the effectiveness and superiority of our method.

The Digital Linguistics: The Birth of Linguistic Humans 66,000 Years Ago in South Africa with Laryngeal Descent

Modern humans are linguistic humans, who acquired the logical properties of phonemes and morae in speech sound to generate an infinite number of word signs and to compose grammatically modulated sentences with complex meanings. 5KA (thousand years ago) they invented characters, which could display individual knowledge and intelligence to be shared and passed on to the following generations. Civilization itself is the linguistic phenomenon where knowledge and thoughts are transferred to subsequent generations via written documents, and very rapid consecutive innovations take place. In the 21st century, we are at the third and final stage of logical linguistic evolution with the interactive search and electric transfer of information via computer networks. It is necessary to clarify the in-brain mechanism for linguistic processing and intelligence to take full advantage of the final stage. The author outlines on the general overview of Digital Linguistics (DL) and identifies the birth of linguistic humans at the time of the laryngeal descent, which provided vowel accented syllables containing logical properties of phonemes and morae, to 66KA on the southern coastline of South Africa at the beginning of Howiesons Poort industry.

Feature Extraction of Dynamic Sign Language Based on Dct

Sign language is the basic way to communicate and understand ideas among people with disabilities, deaf and dumb, and to recognize and understand the meanings of the motions and the gestures used by them that requires knowledge of certain features such as hand position, form, motion, directions and facial expressions. Moreover, the extraction of image features is important and it plays a vital role in further analysis of image processing. Extracting the special features of the isolated Arabic sign language (ArSL) words based on Discrete Cosine Transform (DCT) was proposed in current paper. By monitoring and tracking the trajectory of the hands when single hand movement or double hands extract the required features. That is the independent sign language word features vector is incorporated as an input into the classification stage to derive the meaning of the word as voice or text. The research data were collected in cooperation with the Ministry of Labor and Social Affairs of Iraq with the assistance of the Special Needs Department and up to 40 words of isolated sign language collected. Two signs were taken as examples of feature extraction (Happy and water). Since the word happy gives an example of a sign word performed by two hands, on the other hand, the word water is performed with one hand, the Arabic sign language contains different words, part of them are performed with one hand and the other part with both hands.

WiSign

In this article, we propose WiSign that recognizes the continuous sentences of American Sign Language (ASL) with existing WiFi infrastructure. Instead of identifying the individual ASL words from the manually segmented ASL sentence in existing works, WiSign can automatically segment the original channel state information (CSI) based on the power spectral density (PSD) segmentation method. WiSign constructs a five-layer Deep Belief Network (DBN) to automatically extract the features of isolated fragments, and then uses the Hidden Markov Model (HMM) with Gaussian mixture and Forward-Backward algorithm to recognize sign words. In order to further improve the accuracy, WiSign also integrates the language model N-gram, which uses the grammar rules of ASL to calibrate the recognized results of sign words. We implement a prototype of WiSign with commercial WiFi devices and evaluate its performance in real indoor environments. The results show that WiSign achieves satisfactory accuracy when recognizing ASL sentences that involve the movements of the head, arms, hands, and fingers.

The Three Stage Digital Evolution of Linguistic Humans

Digital Linguistics (DL) is an interdisciplinary study that identifies human language as a digital evolution of mammal analog vocal sign communications, founded on the vertebrate spinal sign reflex mechanism [Tokumaru 2017 a/b, 2018 a/b/c/d]. Analog signs are unique with their physical sound waveforms but limited in number, whilst human digital word signs are infinite by permutation of their logical property, phonemes. The first digital evolution took place 66,000 years ago with South African Neolithic industries, Howiesons Poort, when linguistic humans acquired a hypertrophied mandibular bone to house a descended larynx for vowel accented syllables containing logical properties of phonemes and morae. Morae made each syllable distinctive in the time axis and enabled grammatical modulation by alternately transmitting conceptual and grammatical syllables. The sign reflex mechanism is an unconscious self-protection and life-support mechanism, operated by immune cell networks inside the ventricle system. DL identified cellular and molecular structures for the sign (=concept) device as a B lymphocyte (or, in other words, Mobile Ad-Hoc Networking Neuron), connects to sensory, conceptual and networking memories, which consist of its meanings [Table 1]. Its antibodies can network with antigens of CSF-Contacting Neurons at the brainstem reticular formation and of Microglia cells at the neocortex [Figure 1]. It is plausible that the 3D structure of the antigen molecule takes the shape of word sound waveform multiplexing intensity and pitch, and that specifically pairing the antibody molecule consists of three CDRs (Complementality Defining Regions) in the Antibody Variable Region network with the logic of dichotomy and dualism. As sign reflex deals with survival issues such as food, safety and reproduction, it is stubborn, passive and inflexible: It does not spontaneously look for something new, and it is not designed to revise itself. These characteristics are not desirable for the development of human intelligence, and thus are to be overcome. All the word, sensory and network memories in the brain must be acquired postnatally through individual learning and thought. The reason and intelligence of humans depend on how correctly and efficiently humans learn new words and acquire appropriate meanings for them.

An Acoustic Study of Fundamental Frequency and Pauses in Depressive Teenagers in Thailand: A Pilot Study

Depression is a major public health problem among Thais. It has been reported that 30% of 70 million people living in Thailand suffer from depression. Suicide is a potential end result from mental illness, which normally involves depression. Diagnosis and treatment are key factors in the prevention of depression. In traditional diagnosis, there are two key methods of testing: (i) a screening test and interview and (ii) a biomarker test. In recent years, detecting depression with speech—a kind of biomarker test— has gained high acceptance. Cues of suprasegments in speech, such as pauses, loudness, tones, rhythm, and phonation, have been scientifically proven using acoustic methods of being indicators of depression. This paper has two main objectives: (i) to conduct a review of the use of suprasegments as cues and an analysis of the cues capable of indicating depression in Thailand and (ii) to analyze an acoustic study of pitch measured by the fundamental frequency and silent pause length in depressed and non-depressed participants. The method used in the study is the acoustic method of linguistics. Praat program version 6.2.09 was used to analyze the data. This is a pilot study of three depressed Thai students aged 20 compared with three non-depressed Thai participants. We propose a new perspective upon Thai language speech indicators that combines two or more cues in detecting depression (e.g. depression inventory with pause duration and word signs). Interestingly, it was found that the pitch of Thai tones may not be an appropriate cue for depression in Thais. This result conflicts with previous research conducted in other non-tonal languages. The results of this study lay the foundation for a Thai speech index for depression that can be further developed for the detection of depression.

Hand sign language recognition using multi-view hand skeleton

Hand sign language recognition from video is a challenging research area in computer vision, which performance is affected by hand occlusion, fast hand movement, illumination changes, or background complexity, just to mention a few. In recent years, deep learning approaches have achieved state-of-the-art results in the field, though previous challenges are not completely solved. In this work, we propose a novel deep learning-based pipeline architecture for efficient automatic hand sign language recognition using Single Shot Detector (SSD), 2D Convolutional Neural Network (2DCNN), 3D Convolutional Neural Network (3DCNN), and Long Short-Term Memory (LSTM) from RGB input videos. We use a CNN-based model which estimates the 3D hand keypoints from 2D input frames. After that, we connect these estimated keypoints to build the hand skeleton by using midpoint algorithm. In order to obtain a more discriminative representation of hands, we project 3D hand skeleton into three views surface images. We further employ the heatmap image of detected keypoints as input for refinement in a stacked fashion. We apply 3DCNNs on the stacked features of hand, including pixel level, multi-view hand skeleton, and heatmap features, to extract discriminant local spatio-temporal features from these stacked inputs. The outputs of the 3DCNNs are fused and fed to a LSTM to model long-term dynamics of hand sign gestures. Analyzing 2DCNN vs. 3DCNN using different number of stacked inputs into the network, we demonstrate that 3DCNN better capture spatio-temporal dynamics of hands. To the best of our knowledge, this is the first time that this multi-modal and multi-view set of hand skeleton features are applied for hand sign language recognition. Furthermore, we present a new large-scale hand sign language dataset, namely RKS-PERSIANSIGN, including 10′000 RGB videos of 100 Persian sign words. Evaluation results of the proposed model on three datasets, NYU, First-Person, and RKS-PERSIANSIGN, indicate that our model outperforms state-of-the-art models in hand sign language recognition, hand pose estimation, and hand action recognition.

Development of The AR School App for Children with Hearing Impairment Who Begin Learning Ecuadorian Sign Language using Augmented Reality

Augmented reality AR has been used for many years in different fields of education. It has provided advantages in learning, However, no applications focused on the initial learning of Ecuadorian sign language for children with hearing impairments in their primary school years have been found. In this paper we present the development of a mobile application based on augmented reality, the Unity tool was used as a platform for mobile devices and the Vuforia SDK complement for augmented reality. With this application, the child can see the gesticulation of words in sign language through the use of printed templates. It also has an option to perform a quiz that will allow it to evaluate the knowledge the children acquired from the learning module. The mobile application called ARSchool based on augmented reality which is designed and adapted for people with hearing impairment, mainly for school-age children, as support for the initial learning of sign language in Ecuador. Once the application was developed, it was tested both at school and at home, in which teachers and parents made children with hearing impairments interact.

Hear Sign Language: A Real-time End-to-End Sign Language Recognition System

Sign language recognition (SLR) bridges the communication gap between the hearing-impaired and the ordinary people. However, existing SLR systems either cannot provide continuous recognition or suffer from low recognition accuracy due to the difficulty of sign segmentation and the insufficiency of capturing both finger and arm motions. The latest system, SignSpeaker, has a significant limit in recognizing two-handed signs with only <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">one</i> smartwatch. To address these problems, this paper designs a novel real-time end-to-end SLR system, called DeepSLR, to translate sign language into voices to help people “hear” sign language. Specifically, two armbands embedded with an IMU sensor and multi-channel sEMG sensors are attached on the forearms to capture both coarse-grained arm movements and fine-grained finger motions. We propose an attention-based encoder-decoder model with a multi-channel convolutional neural network (CNN) to realize accurate, scalable, and end-to-end continuous SLR without sign segmentation. We have implemented DeepSLR on a smartphone and evaluated its effectiveness through extensive evaluations. The average word error rate of continuous sentence recognition is 10.8 percent, and it takes less than 1.1s for detecting signals and recognizing a sentence with 4 sign words, validating the recognition efficiency and real-time ability of DeepSLR in real-world scenarios.

What of the Land with Bows? Archers of “Meshech” and the Allusion to Genesis in Isaiah 66:19

This paper seeks to interpret a unique gentilic in the Book of Isaiah. Placed with what in redactional methodology is referred to as Trito-Isaiah, Isaiah 66:19 lists several names of nations and among them is a certain Mosḵe qeset, translated as of the bow. Meshech is a reference to Phrygia between Lydia and Tubal/Tabal in Central Anatolia. Although the term may be assumed for Meshech, it is not something specific to them in ancient Near Eastern, ancient Greek or Hebrew Bible tradition. The referece to the bow in Isaiah 66:19 can be understood as a marker for a literary allusion to Genesis 9:13. The use of another marker in the Masoretic text, the word sign (ot) in both Isaiah 66:19 and Genesis 9:13 further strengthens this interpretation.

I-Sign: Sign Language Learning Application Via Gamification

Hearing loss is a type of disability where people who suffer from it could not hear a sound or can only listen to a sound with certain levels. People with hearing loss use sign language to communicate with others and to help them in their learning process. For this study, an interview and survey were conducted with teachers and students from SK Pendidikan Khas Melaka and few problems have been identified in the learning spectrum of children with hearing disability. They face difficulties in learning due to the lack of exposure about the correct sign language since young, difficulty in interpreting sign language in the conventional teaching material due to the nature of its static image contents, and hearing loss children are also usually less focused in the learning process and are easily distracted by their surroundings when the class is in session. To solve these problems, i-Sign is developed as a learning application that incorporates simple gamification in its development that could help hearing loss children to learn the alphabet and basic words of sign language. The use of gamification and multimedia elements provide a more interactive and fun learning environment for the students instead of using static contents, and are also used to direct students’ attention to the learning activity making them more focused in the learning process. i-Sign was developed using the ADDIE model which includes the Analysis, Design, Development, Implementation, and Evaluation phases. In the evaluation phase, a usability test was conducted on 8 children with hearing loss to test the acceptance of the user towards this application and 91.89% of the respondents found that the application meets their expectation of the application capability in terms of its effectiveness, efficiency and user satisfaction. This shows that gamification can be used as an alternative learning material for hearing loss children and help expose the correct sign language to them. The application can also be used by the public that wants to learn about sign language.