Language Recognition Research Articles

Assistive Communication Web App: A Multi-Model Solution for Individuals with Disabilities”

The Assistive Communication Web App is an innovative platform designed to address the communication challenges faced by individuals with speech, hearing, and motor impairments. By integrating advanced technologies such as speech recognition, head-gaze tracking, and gesture-based sign language recognition, the app provides real-time speech-to-text, text-to-speech, and gesture-to-text functionalities. This research outlines the app's system architecture, methodology, and user interface, emphasizing its potential to enhance accessibility and empower users with greater independence. Through its multi-modal approach, the web app fosters inclusivity and sets a new benchmark for assistive technologies. Keywords: Assistive communication, Speech-to-text, Text-to-speech, Sign language recognition, Head gaze tracking, WebGazer.js, Real-time interaction, Gesture recognition, MediaPipe FaceMesh, TensorFlow HandPose, Web Speech API, Real-time transcription, Multilingual support, Cross-platform compatibility, Emotion detection, User-centered design, Modular architecture

Improved feature reduction framework for sign language recognition using autoencoders and adaptive Grey Wolf Optimization

Automatic Sign Language Recognition Systems (ASLR) offers smooth communication between hearing-impaired and normal-hearing individuals, enhancing educational opportunities for impaired. However, it struggles with “curse of dimensionality” due to excessive features resulting in prolonged training time and exhaustive computational demand. This paper proposes technique that integrates machine learning and swarm intelligence to effectively address this issue. The proposed technique, initially, extracts features using histrogram of gradient (HOG) approach and then reduces dimensions of extracted features using unsupervised autoencoder and subsequently refining the feature set with an improved GWO algorithm. A handcrafted artificial neural network serves as the classifier within this integrated framework, denoted as AEGWO-Net. Exhaustive experimentations were conducted on six different datasets namely ASL, ASL MNIST, ISL, ArSL, MNIST Digits, and IEEE-ISL containing gestures of different languages to demonstrate the performance of AEGWO-Net. The AEGWO-Net demonstrates superior performance improving accuracy and F1 score by 6% and 4% respectively compared to PCA-IGWO and KPCA-IGWO algorithms. Achieving high accuracy (98.40%), F1-score (96.59%), MCC (97.14%), and AUC (96.21%) indicates the robustness and generalizability of the AEGWO-Net method even with reduced dimensionality. Furthermore, a comparison between AEGWO-Net with other existing swarm intelligence techniques is also made to demonstrate its superiority.

Talking Fingers: A Multilingual Speech-to-Sign Language Converter

Communication is a basic human need, but thousands of people with hearing and speech impairments face limitations in everyday communication "Talking Fingers" is a modern assistive technology tool that transfers spoken or written language to Indian Sign Language (ISL). With multilingual capabilities, the tool provides technologies such as Google ML Kit for language recognition, MyMemory API for translation, ISL grammar services for more than one language and several languages accessible at a time Translated ISL will, a it provides a simple and powerful communication channel. The system outlines the ability to blend artificial intelligence (AI) and language generation to promote inclusion and empower individuals with disabilities

Triboelectric Bending Sensors for AI-Enabled Sign Language Recognition.

Human-machine interfacesand wearable electronics, as fundamentals to achieve human-machine interactions, are becoming increasingly essential in the era of the Internet of Things. However, contemporary wearable sensors based on resistive and capacitive mechanisms demand an external power, impeding them from extensive and diverse deployment. Herein, a smart wearable system is developed encompassing five arch-structured self-powered triboelectric sensors, a five-channel data acquisition unit to collect finger bending signals, and an artificial intelligence (AI) methodology, specifically a long short-term memory (LSTM) network, to recognize signal patterns. A slider-crank mechanism that precisely controls the bending angle is designed to quantitively assess the sensor's performance. Thirty signal patterns of sign language of each letter are collected and analyzed after the environment noise and cross-talks among different channels are reduced and removed, respectively, by leveraging low pass filters. Two LSTM models are trained using different training sets, and four indexes are introduced to evaluate their performance, achieving a recognition accuracy of 96.15%. This work demonstrates a novel integration of triboelectric sensors with AI for sign language recognition, paving a new application avenue of triboelectric sensors in wearable electronics.

Artificial Intelligence based Automated Sign Gesture Recognition Solutions for Visually Challenged People

Gesture recognition is employed in human-machine communications, enhancing human life with impairments or who depend on non-verbal instructions. Hand gestures role an important role in the field of assistive technology for persons with visual impairments, whereas an optimum user communication design is of major importance. Many authors with substantial development for gesture recognition modeled several methods by using deep learning (DL) methods. This article introduces a Robust Gesture Sign Language Recognition Using Chicken Earthworm Optimization with Deep Learning (RSLR-CEWODL) approach. The projected RSLR-CEWODL algorithm majorly focuses on the recognition and classification of sign language. To accomplish this, the presented RSLR-CEWODL technique utilizes a residual network (ResNet-101) model for feature extraction. For optimal hyper parameter tuning process, the presented RSLR-CEWODL algorithm exploits the CEWO algorithm. Besides, the RSLR-CEWODL technique uses a whale optimization algorithm (WOA) with deep belief network (DBN) method for the sign language recognition method. The simulation result of the RSLR-CEWODL algorithm is tested using sign language datasets and the outcome was measured under various measures. The simulation values demonstrated the enhancements of the RSLR-CEWODL technique over other methodologies.

Ultra-adhesive iontronic hydrogels strengthened by folded protein for flexible transducer with language recognition capabilities

Ultra-adhesive iontronic hydrogels strengthened by folded protein for flexible transducer with language recognition capabilities

Enhanced EEG Signal Classification Using Machine Learning and Optimization Algorithm

This paper proposes a better solution for EEG-based brain language signals classification, it is using machine learning and optimization algorithms. This project aims to replace the brain signal classification for language processing tasks by achieving the higher accuracy and speed process. Features extraction is performed using a modified Discrete Wavelet Transform (DWT) in this study which increases the capability of capturing signal characteristics appropriately by decomposing EEG signals into significant frequency components. A Gray Wolf Optimization (GWO) algorithm method is applied to improve the results and select the optimal features which achieves more accurate results by selecting impactful features with maximum relevance while minimizing redundancy. This optimization process improves the performance of the classification model in general. In case of classification, the Support Vector Machine (SVM) and Neural Network (NN) hybrid model is presented. This combines an SVM classifier's capacity to manage functions in high dimensional space, as well as a neural network capacity to learn non-linearly with its feature (pattern learning). The model was trained and tested on an EEG dataset and performed a classification accuracy of 97%, indicating the robustness and efficacy of our method. The results indicate that this improved classifier is able to be used in brain–computer interface systems and neurologic evaluations. The combination of machine learning and optimization techniques has established this paradigm as a highly effective way to pursue further research in EEG signal processing for brain language recognition.

Analyzing Algorithms for Sign Language Modeling: A Tale of Development

The rapid advancement of assistive technologies has revolutionized accessibility for individuals with disabilities, particularly through innovations in sign language recognition and modeling. Sign languages, characterized by intricate combinations of hand gestures, facial expressions, and body movements, present unique computational challenges due to their multimodal and spatially complex nature. This study systematically reviews the evolution of algorithms in sign language recognition, examining the strengths and limitations of rule-based, machine learning, and deep learning approaches. The findings highlight the transformative potential of deep learning models, especially multimodal systems, while underscoring persistent challenges such as dataset scarcity, computational demands, and regional variability in sign languages. By synthesizing trends and identifying gaps, this research contributes actionable insights to the development of inclusive, efficient, and universal sign language recognition systems, supporting global accessibility goals.

CONSTITUTIONAL RECOGNITION OF THE KURDISH LANGUAGE IN IRAQ BETWEEN THEORY AND PRACTICE (AN ANALYTICAL STUDY)

The Republic of Iraq is a multi-ethnic federal state, and the Kurdish language is one of the main constitutional languages ​​of its ethnic components. This language has its own rules, roots and history, but at most stages and different times, the official authorities in the country ignored this language or did not pay sufficient attention to it through formulating the legal procedures for determining the official language. Since the issuance of the Basic Law of 1925, the policy of one official language has been followed at the national level, which was the Arabic language, while taking into account ethnic and linguistic diversity at a lower and narrower level. The recognition of the Kurdish language as an official language in Iraq was a sensitive political issue. At some stages it was recognized indirectly within the framework of national rights, and at other stages directly but only in areas inhabited by Kurds and the Kurdistan Region. However, with the establishment of the federal system, especially after the issuance of the 2005 Constitution, the Kurdish language, along with the Arabic language, became an official language throughout the Republic of Iraq, and it was an important step to strengthen a constitutional right for an ethnic component in Iraq. To ensure the consolidation of constitutional recognition of the Kurdish language, some legal and practical texts and procedures were put in place, while on the practice, it faced many obstacles and was not implemented as required, so that the imposition and use of the Arabic language appears clearly through the actions and dealings of the federal authorities throughout Iraq, and this violates the principles of the current Iraqi Constitution, and is considered a return to the pre-federal period.

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.

National and Ethnic Identity in the Constitutions of the BRICS Countries

The article presents the transformation of the concept of ethnicity, which is evident in many countries across the world in the context of changing world order. The author demonstrates the tendency to accept poly ethnicity and multiple faces in modern states, including the BRICS countries. Also, the author examines various approaches to defining ethnicity that exist both in legal science and in other social sciences. Using the example of the BRICS countries, it is shown that the legal recognition of ethnic identity, language and cultural differences occurs at the level of national constitutions since these categories are essential for recognition and awareness of each citizen and each national society in existing multinational states. The author proves that the formation of constitutional and legal norms taking into account the essence of ethnicity will contribute to the sustainable development of multinational states.

Development and Application of Artificial Intelligence Multimedia Technology Based on Big Data

Artificial intelligence is an innovative enterprise theme that combines computer science, physiology, science, and other disciplines, including expert programs, technical experiments, games, native language understanding, cognitive rehabilitation, robotics, engineering, recognition, and other fields. The breakthrough growth made the arrival of the era of big data have a fundamental impact on many traditional industries and has also promoted the transformation of teaching methods and methods in the field of education. In the traditional classroom, due to the limitations of teaching resources, teaching time, and location, students are basically passively accepted by the teacher, and the teaching form is single. This will improve in the age of big data with well-developed network message. Modern distance education uses advanced technology such as computer networks, multimedia, and artificial intelligence to build a virtual teaching environment based on the network. It breaks through the limitations of teachers, teaching materials, experimental equipment, and other resources that exist under the traditional teaching model. Using educational resources of the same scale can expand educational capabilities exponentially and at the same time overcomes the unified progress of traditional teaching methods, single teaching methods, and students’ dissatisfaction. In this research we developed a system based on intelligent multimedia method and have the characteristics of security and stability and have done some help for network teaching of educational institutions.

Continuous sign language recognition enhanced by dynamic attention and maximum backtracking probability decoding

Continuous sign language recognition enhanced by dynamic attention and maximum backtracking probability decoding

Wearable Electronic Glove and Multilayer Para-LSTM-CNN-Based Method for Sign Language Recognition

Wearable Electronic Glove and Multilayer Para-LSTM-CNN-Based Method for Sign Language Recognition

Where Can I Sign My Language?: A Systematic Literature Review (2000–2019) of Young People's Access to Sign Language Socialisation Spaces in the Nordic Countries

This article presents the results from a systematic literature review of Nordic research studies from 2000 to 2019, addressing the question of children and adolescents' access to spaces where they can sign with peers and adults. The study is based on a dialogistic approach to language, and holds that languaging is inextricably tied to places and situations—that is, spaces and contexts in which people participate in interactions with others. Thus, acquiring sign language is not only about the child or adolescent's individual learning of sign language in an educational setting, but also about participation in sign language activities. The review addresses the paradoxical situation in the field of sign language education whereby formal recognition of sign language and the institutionalisation of rights to sign language education gained momentum at around the same time as the number of deaf schools began to decline. The results from the review indicate that very few studies of sign language pay attention to spaces where children and adolescents can interact with other people through sign language. It appears that current legislation, as well as research, emphasises the individual right to learn sign language for deaf and hard-of-hearing children, and has overlooked the significance of facilitating and protecting sign language-based socialisation spaces as significant sites for sign language learning, participation and acquisition.

A corpus-based critical discourse analysis of language ideologies in parliamentary debates about the recognition of Irish sign language

ABSTRACT Irish Sign Language (ISL) became an officially recognised language in Ireland by means of the ISL Act 2017, which commenced in December 2020 after more than 30 years of campaigning by the Deaf community. While some work has investigated language ideologies behind the ISL recognition campaign, this study explores language ideologies in parliamentary discourse, specifically perspectives of languageness of ISL. This is crucial to the study of sign language recognition and policymaking, as previous research has identified a link between differing views on sign languages and deafness and policy outcomes. A corpus of parliamentary debates on ISL recognition (2013-2020) was compiled and analysed. A sociocognitive approach was adopted, alongside a framework for analysing how discourses establish legitimacy for social practices. Theoretically, categories of sign language ideologies were applied. A link between language, culture and identity is established by the legislators through their use of terms such as 'indigenous' and 'native' to describe ISL and the Deaf community. ISL is compared to Irish to further their argument and claims are made about the capability of ISL as a legitimate language. Finally, benefits of ISL to wider society are highlighted.

A Chinese sign language recognition system combining attention mechanism and acoustic sensing

In recent years, with the widespread popularity of smart devices and the rapid development of communication and artificial intelligence technologies, sign language gestures that can break the communication barriers between ordinary people and those with speech and hearing impairments have received much attention. However, existing human gesture recognition methods include wearable device-based, computer vision-based and Radio Frequency (RF) signal-based. These methods have problems of being difficult to deploy, violating user privacy, and being susceptible to ambient light. Compared with the above methods, using ultrasonic signals to sense sign language gestures has the advantages of not violating user privacy and not being affected by ambient light. For that purpose, we use the built-in speaker and microphone of a smartphone to send and receive ultrasonic signals to recognize sign language gestures. In order to recognize fine-grained sign language gestures, we calculate the Channel Impulse Response (CIR) induced by the sign language action as a sign language gesture special. After that, we compute first-order differences along the time dimension of the Channel Impulse Response matrix to eliminate static path interference. Finally, a convolutional neural network containing convolutional layers, spatial attention, and channel attention is passed in order to recognize sign language gestures. The experimental results show that the scheme has a recognition accuracy of 95.2% for 12 sign language interaction gestures.

Occlusion Resistant Spatio-Temporal Hybrid Cue Network for Indian Sign Language Recognition and Translation

Objective: To tackle the issues of occlusion in human skeleton extraction and simplify the pixel matching related to the human skeleton structure for efficient Indian Sign Language (ISL) recognition and translation. Methods: This paper presents Occlusion-Resistant STHCN (OSTHCN) to tackle the occlusion problem in human skeleton extraction for effective ISL recognition and translation. This model incorporates Skeleton Occupancy Likelihood Map estimation using B-Spline curves to enhance the skeleton extraction. Due to occlusions caused by fingers and hands, the extracted skeleton is composed of disconnected skeletal subgraphs. Consequently, each observed skeleton is represented as a probability distribution along an ellipsoidal contour, originating from the central points of the skeleton. A heuristic technique estimates occluded skeletons using 3D probability map with an occupancy grid where each voxel indicates skeleton likelihood. The occupancy distribution is updated using observed branch clusters across image sequences, detecting occluded skeletons by finding minimum-cost paths. Finally, Maximally connected subgraphs are merged into a main graph by finding minimum-cost paths in the 3D likelihood map, enabling the prediction of occluded skeleton parts for ISL recognition and translation. Findings: OSTHCN model achieved an accuracy of 96.74% on the ISL Continuous Sign Language Translation Recognition (ISL-CSLTR) dataset outperforming existing prediction models. Novelty: This model employs a unique occlusion-handling strategy for skeleton extraction, estimating occluded part, integrating connected subgraphs via minimal cost path searches for more precise skeleton parts and enhancing accuracy for ISL recognition and translation. Keywords: Sign Language, Graph Convolutional Neural Network, Ellipsoidal Contour, 3D Likelihood Map, Occupancy Probability

A hybrid CNN-random forest model with landmark angles for real-time Arabic sign language recognition

A hybrid CNN-random forest model with landmark angles for real-time Arabic sign language recognition

A real-time platform for Spanish Sign Language interpretation

AbstractMore than 13% of the Spanish population suffers from hearing impairment. Despite the existence of several hearing aids and implants making sounds clearer and louder, there are some people unable to use them and, consequently, their only means of communication is Sign Language. However, this language is not widely known in the society. Consequently, those who are deaf or hard of hearing may be socially excluded and experience frustration as a result of the lack of communication. In this context, Sign Language Recognition and interpretation would help to break down the existing communication barriers and facilitate the creation of inclusive environments. With that aim, this paper presents a real-time platform to recognize and interpret finger-spelt words in Spanish Sign Language (Lengua de Signos Española). As finger spelling implies the recognition of each signed letter, a comparative analysis of different deep learning techniques to properly recognize the Spanish Sign Language alphabet has been carried out. For that, due to the lack of Spanish Sign Language datasets, the first step was to capture and build an image dataset representing its 30 letters. As there are static and in-motion letters, spatial and temporal analysis has been conducted by considering different kind of neural networks (Convolutional Neural Networks, Recurrent Neural Networks, and Vision Transformers). The experimental results highlight the good performance of the studied architectures, obtaining a maximum accuracy of 79.96% on previously unseen data. Finally, a real-time platform for the recognition and interpretation of finger-spelt words in Spanish Sign Language has been implemented making the communication possible.