Alphabetic Languages Research Articles

Malaysian Sign Language Detection with Convolutional Neural Network for Disabilities

Sign language is the main form of communication used by deaf people. Most of their activities like speaking and learning involved sign language. In Malaysia, instead of a deaf person, only a few people know sign language because it's not part of the co-curriculum. Hence, normal people need to know sign language so that they can communicate with deaf people effectively. However, learning sign language requires a lot of effort and takes years of study. Therefore, this research tends to initiate the sign language image detection system that utilizes the deep learning model. The initial effort involves the development of an image detection system that can identify the alphabet of sign language from A to Z. There will be 26 alphabets that contribute to 26 classes of image detection using the Convolutional Neural Network. 85 images will be collected for each alphabet and the total data will be distributed into 80% and 20% for training and testing the CNN model, respectively. The result showed that the proposed system produced more than 95% detection accuracy of the alphabet based on finger sign gestures. For future works, the proposed system will be evaluated with a more complex dataset in terms of words.

Orthographic and phonological processing in the left ventral occipitotemporal cortex during Chinese word reading.

The left ventral occipitotemporal cortex (lvOT) has been consistently identified as a crucial structure in word reading, and its function varies across subregions. Nevertheless, the specific function of the lvOT and its subregions remains controversial because the obvious grapheme-to-phoneme correspondence rules of alphabetic languages make it difficult to disentangle the contributions of orthography and phonology to neural activations. To explore information processing in lvOT subregions, the present study manipulated the orthography and phonology in a factorial design and used the fMRI rapid adaptation paradigm. The results revealed a posterior-to-anterior functional gradient in lvOT in Chinese word reading and specified that the functional transition from sublexical to lexical processing occurred in the middle subregion close to the classic VWFA. More importantly, we found that the middle and posterior subregions of lvOT are responsible for processing both orthographic and phonological information during Chinese word reading. These results elaborated the function of the lvOT in Chinese word reading.

Transfer learning with YOLOV8 for real-time recognition system of American Sign Language Alphabet

Sign language serves as a sophisticated means of communication vital to individuals who are deaf or hard of hearing, relying on hand movements, facial expressions, and body language to convey nuanced meaning. American Sign Language (ASL) exemplifies this linguistic complexity with its distinct grammar and syntax. The advancement of real-time ASL gesture recognition has explored diverse methodologies, including motion sensors and computer vision techniques. This study specifically addresses the recognition of ASL alphabet gestures using computer vision through Mediapipe for hand movement tracking and YOLOv8 for training the deep learning model. The model achieved notable performance metrics: precision of 98%, recall rate of 98%, F1 score of 99%, mean Average Precision (mAP) of 98%, and mAP50-95 of 93%, underscoring its exceptional accuracy and sturdy capabilities.

Critique of Colonialism and Cultural Imperialism in Selected Poems of Tanveer Anjum from Nai Zaban Kay Huroof Alphabet of a New Language

Postcolonial complexity of thought is an integral discourse in Pakistani writers’ works. Tanveer Anjum is a contemporary Pakistani Urdu poetess and her poetry is perceptive of personal, social and political concerns of modern times. In a postcolonial country, the colonial past is never detached from the common consciousness and the unending imperialism and post war traumas are part of its subjects’ collective memories. Five poems are selected from her recent collection of Urdu poetry, Nai Zaban kay Huroof (Alphabet of a New Language) for the postcolonial analysis. The poems are: ‘Interview’, ‘There Was a Village’, ‘The Last Nail’, ‘Sister Caroline’s Dappled Cats’ and ‘Like Sunbeams’. The research is qualitative in nature and the theories of Edward Said and Homi K. Bhabha are used for the textual analysis of the selected poems. The analysis reveals a parallel structure of thoughts in her poems which at one side endorses the need of cultural resistance and on the other, calls for a negotiation, which further affirms the complexities of postcolonial thought process.

Multimodal reading in reading-only versus reading-while-listening modes: evidence from Chinese language learners

Abstract Language educators and researchers have shown keen interest in enhancing second language (L2) learners’ reading skills, and recently, more emphasis has been placed on multimodal learning. Multimodal learning theories posit that the confluence of auditory and visual stimuli facilitates learners to establish robust referential connections, and thus integrating audio cues has emerged as a strategy to enhance reading performance. While prior research has affirmed the advantages of incorporating audio cues for fostering reading fluency and comprehension in general, the findings are inconsistent. These investigations have predominantly focused on learners of English as a second language. Considering the differences between English and Chinese, especially their relationship between written scripts and oral language, investigating the reading experiences of Chinese language learners can contribute to a fuller understanding of the effect of audio inclusion on L2 learners. This study compared reading comprehension and reading experiences in reading-only and reading-while-listening modes for intermediate-low and intermediate-high-level Chinese language learners. After learners read in two different modes, a T-test was conducted on their comprehension performance followed by a qualitative analysis of their perspectives on their reading experiences. The findings showed a significant influence of audio integration on enhancing reading comprehension among intermediate-low-level Chinese language learners engaged in multimodal Chinese reading, and these learners displayed a preference for audio inclusion. On the other hand, a lack of significance in the effects of supplementary audio cues on reading comprehension was identified for intermediate-high-level learners, who manifested a mixed attitude towards audio integration with reading. This study complements the existing understanding of multimodal reading based on alphabetic language, particularly in English. Moreover, the findings carry pertinent implications for Chinese language reading pedagogy.

Examining Relationships Between Sub-Components of Reading in Xitsonga

Reading is developed over time and involves the interaction of both simple and complex skills characterised by a hierarchical sequence of foundational reading skills. However, research has shown that children who do not acquire mastery of foundational reading skills have limited chances of acquiring reading success. This study examines the relations between sub-components of reading in Xitsonga and their impact on Grade 1 learners’ reading ability. It also aims to identify which early reading skills predict later reading accomplishment. Data in this study was obtained from 75 Grade 1 learners in the Limpopo Province. The early-grade reading assessment tool adapted to Xitsonga was used to test the learners’ foundational reading skills: phonological and phonemic awareness, letter-sound knowledge, word reading, oral reading fluency and reading comprehension skills. The results present a compelling relationship between the subcomponents of reading and show that deficits in the development of foundational reading skills negatively impact learners’ ability to read. Regression analysis showed that oral reading fluency was the only significant predictor of reading comprehension. Hence, there is a need for reading to be taught and learned consciously in alphabetic languages to help learners develop their early reading skills, which play important roles in the acquisition of reading.

Implementasi Algoritma You Only Look Once (YOLO) untuk Mendeteksi Bahasa Isyarat SIBI

The Indonesian Sign Language System (SIBI) is a translator of sign language into text or speech. This research aims to bridge communication between ordinary people and speech impaired people through the introduction of SIBI sign language using the YOLO algorithm. This research uses 24 alphabets which are divided into 4 groups, where each alphabet has 20 image data which is divided into 70% train data, 25% valid data, and 5% test data. The train data was then added with augmented data from Roboflow which was then carried out using a training process using a batch number of 16 and epochs of 100. The results of the research show that the YOLO algorithm can detect SIBI sign language alphabet gestures using confusion matrix testing and achieve quite good performance, as shown by the results F1 Score: Group 1 was 90.90%, Group 2 was 97.1%, Group 3 was 90.90%, and Group 4 was 83.8%. Other factors such as hand size, lighting conditions, and variations in data position also affect detection accuracy. A limitation in this research is that the alphabets J and Z were not included because these two alphabets not only use shape patterns, but also gesture patterns.

Gesture recognition technology: a new dimension in human-computer interaction interface

Development of an interface for intelligent gesture control to improve user experience and increase the efficiency of interaction with a computer. This paper proposes a gesture recognition system based on artificial intelligence using convolutional neural networks (CNN). The system comprises three stages: pre-processing, optimal frame determination, and gesture category identification. The extracted features used are independent of movement, scaling, and rotation, providing greater flexibility to the system. The suggested gesture control technology, known as Kazakh Sign Language (KSL) for Kazakh alphabets, eliminates the need for additional devices, enabling users to interact with the system naturally. Experiments demonstrated that the proposed KSL system can accurately recognize Kazakh language alphabet letters with a high precision of 97.3%, owing to the utilization of artificial intelligence and CNN to enhance the accuracy and effectiveness of gesture control. Gestures, a type of visual formation, are perceivable by computers through machine learning models. The selection of methods and systems for recognizing Kazakh sign language gestures was accompanied by addressing various challenges related to language-specific orthographic and gestural features. The developed gesture control interface for human-computer interaction is applied in the field of inclusive education, aiming to assist deaf and hard-of-hearing children in learning sign language.

Alphabet Recognition of American Sign Language Using Machine Learning

A major challenge faced by our society is the difficulty individuals with disabilities encounter in expressing their emotions to others. People with disabilities often depend on sign (gesture) languages for communication. This project aims to develop a model capable of recognizing and translating sign language alphabets from hand gestures into text and audio. The primary objective is to enhance communication between individuals with hearing impairments and the broader society. We assessed our model's performance using a publicly accessible Indian Sign Language (ISL) dataset. For image classification, we employed Convolutional Neural Networks (CNNs) with the Inception V3 architecture. Hand gestures are captured through webcams, and our model identifies the corresponding alphabet for each gesture. This project seeks to overcome current challenges in Sign Language Recognition and aims to enhance its effectiveness and efficiency.

The Optimization of Numerical Algorithm Parameters with a Genetic Algorithm to Animate Letters of the Sign Alphabet

At present, the development of animation-based works for human–computer interaction applications has increased. To generate animations, actions are pre-recorded and animation flows are configured. In this research, from two images of letters of the sign language alphabet, intermediate frames were generated using a numerical traced algorithm based on homotopy. The parameters of a homotopy curve were optimized with a genetic algorithm to generate intermediate frames. In the experiments performed, sequences where a person executes pairs of letters in sign language were recorded and animations of the same pairs of letters were generated with the proposed method. Subsequently, the similarity of the real sequences to the animations was measured using Dynamic Time Wrapping. The results obtained show that the images obtained are consistent with their execution by a person. Animation files between sign pairs were created from sign images, with each file weighing an average of 18.3 KB. By having sequences between pairs of letters it is possible to animate words and sentences. The animations generated by this homotopy-based animation method optimized with a genetic algorithm can be used in various deaf interaction applications to provide assistance. From several pairs of letters a file base was generated using the animations between pairs of letters; with these files you can create animations of words and sentences.

Reviving Ancient Egypt in the Renaissance Hieroglyph: Humanist Aspirations to Immortality

In his On the Art of Building, Renaissance humanist Leon Battista Alberti wrote that the ancient Egyptians believed that alphabetical languages would one day all be lost, but the pictorial method of writing they used could be understood easily by intellectuals everywhere and far into the future. Amidst a renewed appreciation of ancient Egyptian hieroglyphics found on obelisks in Italy and the discovery of Horapollo’s Hieroglyphica, which purported to translate the language, Renaissance humanists like Alberti developed an obsession with this ancient form of non-alphabetical writing. Additionally, a growing awareness of the lost language of their Etruscan ancestors further ignited an anxiety among Italian humanists that their own ideas might one day become unintelligible. As Egyptomania spread through the Italian peninsula, some saw an answer to their fears in the pictorial hieroglyphics of the ancient Egyptians, for they perceived, in Egyptian writing, the potential for a universal language. Thus, many created Renaissance hieroglyphs based on those of the Egyptians. This essay examines the successes and failures of these neo-hieroglyphs, which early modern humanists and artists created hoping that a language divorced from alphabetical text might better convey the memory of their names and contributions to posterity.

DEEP AND MACHINE LEARNING MODELS FOR RECOGNIZING STATIC AND DYNAMIC GESTURES OF THE KAZAKH ALPHABET

Currently, an increasing amount of research is directed towards solving tasks using computer vision libraries and artificial intelligence tools. Most common are the solutions and approaches utilizing machine and deep learning models of artificial neural networks for recognizing gestures of the Kazakh sign language based on supervised learning methods and deep learning for processing sequential data. The research object is the Kazakh sign language alphabet aimed at facilitating communication for individuals with limited abilities. The research subject comprises machine learning methods and models of artificial neural networks and deep learning for gesture classification and recognition. The research areas encompass Machine Learning, Deep Learning, Neural Networks, and Computer Vision. The main challenge lies in recognizing dynamic hand gestures. In the Kazakh sign language alphabet, there are 42 letters, with 12 of them being dynamic. Processing, capturing, and recognizing gestures in motion, particularly in dynamics, pose a highly complex task. It is imperative to employ modern technologies and unconventional approaches by combining various recognition methods/algorithms to develop and construct a hybrid neural network model for gesture recognition. Gesture recognition is a classification task, which is one of the directions of pattern recognition. The fundamental basis of recognition is the theory of pattern recognition. The paper discusses pattern recognition systems, the environment and application areas of these systems, and the requirements for their development and improvement. It presents tasks such as license plate recognition, facial recognition, and gesture recognition. The field of computer vision in image recognition, specifically hand gestures, is also addressed. The development of software will enable the testing of the trained model's effectiveness and its application for laboratory purposes, allowing for adjustments to improve the model.

The Role of Letter-Speech Sound Integration in Native and Second Language Reading: A Study in Native Japanese Readers Learning English.

The automatic activation of letter-speech sound (L-SS) associations is a vital step in typical reading acquisition. However, the contribution of L-SS integration during nonalphabetic native and alphabetic second language (L2) reading remains unclear. This study explored whether L-SS integration plays a similar role in a nonalphabetic language as in alphabetic languages and its contribution to L2 reading among native Japanese-speaking adults with varying English proficiency. A priming paradigm in Japanese and English was performed by presenting visual letters or symbols, followed by auditory sounds. We compared behavioral and event-related responses elicited by congruent letter-sound pairs, incongruent pairs, and baseline condition (symbol-sound pairs). The behavioral experiment revealed shorter RTs in the congruent condition for Japanese and English tasks, suggesting a facilitation effect of congruency. The ERP experiment results showed an increased early N1 response to Japanese congruent pairs compared to corresponding incongruent stimuli at the left frontotemporal electrodes. Interestingly, advanced English learners exhibited greater activities in bilateral but predominantly right-lateralized frontotemporal regions for the congruent condition within the N1 time window. Moreover, the enhancement of P2 response to congruent pairs was observed in intermediate English learners. These findings indicate that, despite deviations from native language processing, advanced speakers may successfully integrate letters and sounds during English reading, whereas intermediate learners may encounter difficulty in achieving L-SS integration when reading L2. Furthermore, our results suggest that L2 proficiency may affect the level of automaticity in L-SS integration, with the right P2 congruency effect playing a compensatory role for intermediate learners.

Advancement in Neural Network Technology for Precise Interpretation of Hand Gestures in Sign Language: A Systematic Review

Abstract: This systematic study investigates the latest developments in neural network technology for effectively understanding hand motions in sign language. It is based on a thorough investigation of 100 academic articles published between 2013 and 2020. Sign language recognition is essential for enabling effective communication and accessibility for those who have hearing problems. In the last ten years, many research articles have presented several neural network models that aim to accurately identify sign language motions. These models have been trained on various datasets, including the American Sign Language (ASL) alphabet and others. The main goal of this study is to conduct a comprehensive evaluation of the effectiveness of current neural network methods in understanding hand movements in sign language. This will be achieved by synthesizing information from reliable and reputable sources in the field. This paper provides a thorough analysis of model architectures, training datasets, assessment measures, and obstacles to provide a complete understanding of the current cutting-edge methodologies. It also highlights possible directions for future research. This research seeks to contribute to the growth of technology-driven solutions for improving communication accessibility and inclusiveness for those with hearing impairments by carefully examining the strengths and limits of neural network-based sign language interpretation systems.

ENCODE CHILDREN IN UKRAINIAN

The article is devoted to the study of the alphabet of the Ukrainian language according to the educational course “My Friends” for children 4-6 years old abroad, which is intended for learning the Ukrainian language at the elementary level (according to the “Standardized requirements for the levels of proficiency in the Ukrainian language as a foreign language A1-C2”): A1 – the initial level, which certifies a partial acquaintance with the structure and system of the Ukrainian language and the possibility of simple, short and thematically limited communication in predicted everyday situations. The article states that the “My Friends” manual is an educational complex that includes: 1. “My Friends”. Educational book. Workbook, part 1; 2. “My friends”. Educational book. Workbook, part 2 and 3. “My friends”. Help for the teacher, online. The focus is on the fact that the educational manual “My Friends” was created in accordance with the New Ukrainian School – a key reform of the Ministry of Education and Science from September 2017 and from February 2018 in accordance with the new Law “On Education”. The manual is intended to help children (aged 4-6 years) familiarize themselves with the Ukrainian alphabet, understand and consolidate the acquired skills of oral and written communication, learn new grammatical models, as well as facilitate the child’s pronunciation of each letter and bring it closer to Ukrainian proper, in general, contribute to the pupil’s development as competent, versatile person. In order for classes to be quite easy and fun, as well as beneficial, the author of the article emphasizes the need to develop a certain strategy and follow it in everything. The educational complex “My Friends” consists of 17 topics and 34 lessons. A separate lesson is developed for each letter in alphabetical order. Each lesson begins with brief information for the teacher: 1. Lesson topic. 2. Determination of the level. 3. The proposed letter. 4. Important words. 5. Situational dictionary. 6. Tasks of the lesson (lexical and grammatical component). 7. Exercises for writing, listening, repeating, speaking and learning letters. We offer to get to know the study guide together with interesting characters (boy Андрій (Andriy), girl Юлія (Yulia) and their pets – Левко (Levko) the lion and Мудрик (Mudryk) the robot). Key words: alphabet, Ukrainian as a foreign language, level A1, foreign language audience, communicative competence.

Learning to Read in an Intermediate Depth Orthography: The Longitudinal Role of Grapheme Sounding on Different Types of Reading Fluency.

Phonological processing skills, such as phonological awareness, are known predictors of reading acquisition in alphabetic languages with varying degrees of orthographic complexity. However, the role of multi-letter-sound knowledge, an important foundation for early reading development, in supporting reading fluency development remains to be determined. This study examined whether two core foundational skills, phonemic awareness and grapheme sounding, have a predictive role in reading fluency development in an intermediate-depth orthography. The participants were 62 children learning to read in European Portuguese, and they were longitudinally assessed on phonemic awareness, complex grapheme sounding, and reading fluency (decoding, word, and text) from Grade 2 to Grade 3. The results showed that grapheme sounding predicted reading fluency development controlled for nonverbal intelligence and vocabulary, short-term verbal memory, and phonemic awareness. Grapheme sounding plays a prominent role in predicting reading fluency outcomes, whereas phonemic awareness (both accuracy and time per correct item) did not contribute to any of the three types of reading fluency. The fact that grapheme-sounding predicted reading fluency is likely due to complex grapheme-phoneme correspondences being required to achieve proficient reading. These findings provide insights into the cognitive processes underlying reading development in intermediate-depth orthographies and have implications for early literacy instruction.

Bridging the Communication Gap - Sign Language Communication System

Now, imagine a world where words are not spoken, and emotions are not expressed. For the Deaf community, this is not a mere thought experiment but a daily reality. Indeed, they are forced to communicate primarily through sign language e, therefore, regularly feel alienated in a society where words are the primary tool for translating thoughts and feelings. Under such circumstances, most Deaf and hard-of-hearing people are struggling to communicate the most effectively. They usually opt for interpreters or their own signaling, but these alternatives are not the most efficient or effective choices. While signaling is the most intuitive and meaningful alternative, its grammar and semantic variations make it impossible to comprehend for those people who are not within the culture. Therefore, we have also developed a software prototype that could interpret sign language automatically. This paper presents a new method to recognize Indian sign language alphabets A-Z and digits (0-9) in a real- time video feed by employing the Bag of Visual Words model (BOVW). Furthermore, it not only predicts the labels of the signs but also gives the output as text and speech. The segmentation process here comprehends skin color detection and background subtraction. Speeded Up Robust FeaturesSurf features have been extracted again from the images, and histograms are built to map the signs to text labels. Furthermore, we have utilized algorithms such as Support Vector Machine (SVM) and Convolutional Neural Networks (CNN) for binary classification. Finally, we have established an interactive Graphical User Interface (GUI to make this process more user-friendly

The word frequency effect in first- and second-language reading by Chinese and Dutch bilinguals

Abstract High-frequency words are processed faster than low-frequency words, known as the word frequency effect (FE). Although the FE has been studied in various writing systems as well as in first- (L1) and second-language (L2) reading, existing theoretical hypotheses are mainly based on findings in alphabetic languages. To date, no study has investigated theoretical explanations of the FE such as the learning hypothesis, the lexical entrenchment hypothesis and the rank hypothesis apply to Chinese–English bilinguals. The present study, therefore, compared the FEs in Chinese– and Dutch–English bilinguals during natural paragraph reading in their L1 and L2, using eye-tracking measures. Chinese bilinguals exhibited a larger FE in L2 than in L1. They displayed smaller L1 FEs and much steeper L2 FE curves than Dutch bilinguals. These findings are not entirely consistent with the existing FE hypotheses, and the present study discusses theoretical accounts in light of the observed results.

Enhancing Arabic Sign Language Recognition using Deep Learning

The present time, Sign language is very important for people who suffer from hearing loss or who cannot speak. Normal humans tend to disregard the significance of signal language, which is a mere supply of communique to mute and deaf societies. So, this study proposes a developed model for sign Language Recognition for Arabic using the Deep learning Convolutional Neural Network (CNN) algorithm. Then set the algorithm by developing programming on Open-CV, using Python language. The dataset contains 54049 snapshots of Arabic signal language alphabets. The 32 folders were created, and each one of them included 1500 images incorporating hand gestures in at-variance environments. The data set was divided into a training section with a percentage of 70 %, a section for testing with a percentage of 20 %, and a section for validation with a percentage of 10 %. The results show that the suggested model achieved an accuracy rate of 94.8%, and it has proven its effectiveness and success, especially after being tried and tested by several users and obtaining their comments and feedback.

American Sign Language Translation from Deaf-Mute People Based on Novel System

This paper presents a system to translate gestures from the American Sign Language alphabet using an instrumented wearable glove. This system represents an attempt to utilize a slide potentiometer in sign language translating. The hardware part of the system consists of five slide potentiometers and two force-sensitive resistors, which are best positioned on a glove, based on the analysis of American Sign Language (ASL) letters. In the software part a neural network is used, which was built and trained using Google Colab and Python as the programming language. The performance of the system was tested on three data sets with different numbers of samples. After that, the letters corresponding to the gestures performed are displayed on a computer screen in real time.