Language Identification Research Articles

Improved Arithmetic Optimization Algorithm with Transfer Learning based Arabic Sign Language Identification System

The Arabic sign language (ArSL) has witnessed ground-breaking research activities to identify hand gestures and signs through the deep learning (DL) model. SL is a unique communication tool that bridges the gaps between people with hearing impairment and ordinary people. The ArSL recognition system is of immense importance for different groups of people since it enables individuals with hearing impairment to communicate effectively. In SLs, signs are characterized by discrepancies in hand positions, shapes, motions, body parts, and facial expressions, posing a crucial threat to visual recognition in computer vision (CV). An automated sign detection technique needs two primary courses of action: the recognition of specific features and the classification of the input dataset. Previously, several approaches for detecting and classifying SLs had been proposed. In this study, an Improved Metaheuristics with Transfer Learning based Arabic Sign Language Identification System (IMTL-ArSL) method is developed. The primary objective of the IMTL-ArSL method is to detect and classify the existence of various signs in the Arabic language. In the IMTL-ArSL model, the bilateral filtering (BF) model is initially used for preprocessing. Besides, the Residual Network (ResNet50v2) model is applied for extracting features, and an improved arithmetic optimization algorithm (IAOA) model is utilized for hyperparameter tuning. Finally, a gated recurrent unit (GRU) network is exploited to identify sign languages. The empirical analysis of the IMTL-ArSL approach is tested using a benchmark dataset. The experimental values of the IMTL-ArSL approach portrayed a superior accuracy value of 93.87% over other techniques.

Implementation of Sibi Sign Language Realtime Detection Program (Case Studi At Sekolah Luar Biasa Negeri 1 Tabanan)

Indonesian deaf people utilize SIBI to communicate using spoken words, gestures, facial expressions, and body language. SIBI, certified for Special Schools (SLB), helps deaf pupils communicate. This project implements SIBI (Indonesian Sign Language System) a real-time detection algorithm at Sekolah Luar Biasa Negeri 1 Tabanan using image processing and YoloV8 ultralytics deep learning. The program trains a sign language gesture detection model on Google Colab's GPU. The SIBI sign language images were used to train a YoloV8 object detection model. The camera captures movements, which the YoloV8 algorithm trained on SIBI gesture data processes. It can recognize gestures in real time and generate text to non-sign language users. The dataset has 107 class vocabulary and 7 class affix prefixes for complete gesture recognition. Shirt color, room brightness, and webcam quality affect detection rates. Optimal detection accuracy is 87.74% and subpar 58.02%. Despite these limitations, the strategy helps deaf students communicate more effectively with non-sign language speakers. This program improves inclusivity and communication in schools, making learning easier for hearing-impaired pupils. This work provides a reliable and quick sign language identification system to help deaf educators and caregivers with daily interactions and education.

OLF-ML: An Offensive Language Framework for Detection, Categorization, and Offense Target Identification Using Text Processing and Machine Learning Algorithms

The pervasiveness of offensive language on social media emphasizes the necessity of automated systems for identifying and categorizing content. To ensure a more secure online environment and improve communication, effective identification and categorization of this content is essential. However, existing research encounters challenges such as limited datasets and biased model performance, hindering progress in this domain. To address these challenges, this research presents a comprehensive framework that simplifies the utilization of support vector machines (SVM), random forest (RF) and artificial neural networks (ANN). The proposed methodology yields notable gains in offensive language detection, automatic categorization of offensiveness, and offense target identification tasks by utilizing the Offensive Language Identification Dataset (OLID). The simulation results indicate that SVM performs exceptionally well, exhibiting excellent accuracy scores (77%, 88%, and 68%), precision scores (76%, 87%, and 67%), F1 scores (57%, 88%, and 68%), and recall rates (45%, 88%, and 68%), proving to be practically successful in identifying and moderating offensive content on social media. By applying sophisticated preprocessing and meticulous hyperparameter tuning, our model outperforms some earlier research in detecting and categorizing offensive language tasks.

“What Is Your Primary Language?”: Spatial Considerations of Primary Language Identification in a Multilingual Rural Region

In small-scale multilingual societies, an individual uses a large number of languages and usually identifies one of them as the primary language. Although empirically observable, primary language has been significantly underexplored, particularly the spatiality of its identification. It is not clear whether and how place is related to why one language might be seen as being more significant than other languages. This study predicts the primary language used by multilingual individuals in an indigenous rural region of Cameroon based on two types of place: the residence of multilingual individuals and the birthplace of their family members. The research goals are supported by a random forest model using spatial-sociolinguistic data of the region. Results show that primary language can be predicted at a high accuracy. The residence of multilingual individuals and the birthplace of their family members capture the spatiality behind primary language identification. This work adds to the current discussion of the space–language connection and is valuable for maintaining the endangered languages in small-scale rural societies.

Whisper-SV: Adapting Whisper for low-data-resource speaker verification

Trained on 680,000 h of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior performance in automatic speech recognition, translation, and language identification. However, its applicability in speaker verification (SV) tasks remains unexplored, particularly in low-data-resource scenarios where labeled speaker data in specific domains are limited. To fill this gap, we propose a lightweight adaptor framework to boost SV with Whisper, namely Whisper-SV. Given that Whisper is not specifically optimized for SV tasks, we introduce a representation selection module to quantify the speaker-specific characteristics contained in each layer of Whisper and select the top-k layers with prominent discriminative speaker features. To aggregate pivotal speaker-related features while diminishing non-speaker redundancies across the selected top-k distinct layers of Whisper, we design a multi-layer aggregation module in Whisper-SV to integrate multi-layer representations into a singular, compacted representation for SV. In the multi-layer aggregation module, we employ convolutional layers with shortcut connections among different layers to refine speaker characteristics derived from multi-layer representations from Whisper. In addition, an attention aggregation layer is used to reduce non-speaker interference and amplify speaker-specific cues for SV tasks. Finally, a simple classification module is used for speaker classification. Experiments on VoxCeleb1, FFSVC, and IMSV datasets demonstrate that Whisper-SV achieves EER/minDCF of 2.22%/0.307, 6.14%/0.488, and 7.50%/0.582, respectively, showing superior performance in low-data-resource SV scenarios.

Language Identifier

This project presents a language identifier system focused on achieving high accuracy in identifying a specific set of 22 languages: Estonian, Swedish, English, Russian, Romanian, Persian, Pashto, Spanish, Hindi, Korean, Chinese, French, Portuguese, Indonesian, Urdu, Latin, Turkish, Japanese, Dutch, Tamil, Thai, and Arabic. Existing LI systems might struggle with the nuances of these languages, often prioritizing identification of more common languages. Our targeted approach allows for tailored optimization to achieve superior accuracy. We employ the Multinomial Naive Bayes (MNB) algorithm due to its effectiveness in text classification tasks and its ability to handle the high-dimensional, sparse features characteristic of LI based on character and word frequencies. The system achieves a promising accuracy of 95% using an 80/20 split for training and testing data. Keywords: Natural Language Processing (NLP), Language Identification (LI), Multinomial Naive Bayes (MNB), Text Classification, Language Barriers, Accuracy, Text Analysis.

Tables and families. Value, emotions and aesthetics of conviviality in two culinary manuscripts of the Mexican elites of the 19th century

ABSTRACT The attributes and cultural meanings of the table as a place for coexistence around food are sources of relevance for the study of the history and daily life of families from the past. The aim of this article is to analyze the social value given by families to the shared act of consuming food at elite 19th-century Mexican tables. This is done through the documentary study of two early and unpublished family culinary manuscripts, handwritten cookbooks created and in use in the period around the declaration of independence of Mexico in 1821. The identification of technical language and words that express affection in recipes, as well as table-mounting related sections in these manuscripts, allows for the assessment of females’ practice or male’s intention of transmitting culinary knowledge orally and in writing. The importance of seasoning as a cultural identity trait is also evident, as well as the weight given by families to affection and aesthetics when transforming, serving, and sharing food in both intimate and public tables. The capacity of Mexican consumption spaces and their associated practices to communicate, maintain or increase prestige is observed as well. These results could be comparable with other environments and historical contexts with similar characteristics and deserve further study.

Speaker-based language identification for Ethio-Semitic languages using CRNN and hybrid features

ABSTRACT Natural language is frequently employed for information exchange between humans and computers in modern digital environments. Natural Language Processing (NLP) is a basic requirement for technological advancement in the field of speech recognition. For additional NLP activities like speech-to-text translation, speech-to-speech translation, speaker recognition, and speech information retrieval, language identification (LID) is a prerequisite. In this paper, we developed a Language Identification (LID) model for Ethio-Semitic languages. We used a hybrid approach (a convolutional recurrent neural network (CRNN)), in addition to a mixed (Mel frequency cepstral coefficient (MFCC) and mel-spectrogram) approach, to build our LID model. The study focused on four Ethio-Semitic languages: Amharic, Ge’ez, Guragigna, and Tigrinya. By using data augmentation for the selected languages, we were able to expand our original dataset of 8 h of audio data to 24 h and 40 min. The proposed selected features, when evaluated, achieved an average performance accuracy of 98.1%, 98.6%, and 99.9% for testing, validation, and training, respectively. The results show that the CRNN model with (Mel-Spectrogram + MFCC) combination feature achieved the best results when compared to other existing models.

Advanced accent/dialect identification and accentedness assessment with multi-embedding models and automatic speech recognition.

The ability to accurately classify accents and assess accentedness in non-native speakers are challenging tasks due primarily to the complexity and diversity of accent and dialect variations. In this study, embeddings from advanced pretrained language identification (LID) and speaker identification (SID) models are leveraged to improve the accuracy of accent classification and non-native accentedness assessment. Findings demonstrate that employing pretrained LID and SID models effectively encodes accent/dialect information in speech. Furthermore, the LID and SID encoded accent information complement an end-to-end (E2E) accent identification (AID) model trained from scratch. By incorporating all three embeddings, the proposed multi-embedding AID system achieves superior accuracy in AID. Next, leveraging automatic speech recognition (ASR) and AID models is investigated to explore accentedness estimation. The ASR model is an E2E connectionist temporal classification model trained exclusively with American English (en-US) utterances. The ASR error rate and en-US output of the AID model are leveraged as objective accentedness scores. Evaluation results demonstrate a strong correlation between scores estimated by the two models. Additionally, a robust correlation between objective accentedness scores and subjective scores based on human perception is demonstrated, providing evidence for the reliability and validity of using AID-based and ASR-based systems for accentedness assessment in non-native speech. Such advanced systems would benefit accent assessment in language learning as well as speech and speaker assessment for intelligibility, quality, and speaker diarization and speech recognition advancements.

Analysis of language identification algorithms for regional Indonesian languages

Detecting local languages in Indonesia is essential for recognizing linguistic diversity, promoting intercultural understanding, preserving endangered languages, and improving access to education and services. By identifying and documenting these languages, we can support language preservation efforts, provide tailored resources for communities, and celebrate the unique cultural heritage of different ethnic groups. Ultimately, this encourages a more accepting and open-minded society, prioritizing various languages and cultural customs. This research aims to identify the most suitable algorithm for language detection in Indonesian regional languages and gain insights into their unique characteristics through n-gram analysis. By understanding language diversity, the study contributes to preserving Indonesia's cultural and linguistic heritage and improving language detection techniques. This study compares the performance of five algorithms (Naïve Bayes, K-nearest neighbors (KNN), least-squares, Kullback Leibler divergence, and Kolmogorov Smirnov test) to determine the most accurate and efficient method for language identification. Incorporating trigram features alongside unigrams and bigrams significantly improved the model's performance, with F1 scores increasing from 0.923 to 0.959. The study found that using more features leads to better accuracy, with Naïve Bayes and KNN emerging as the top-performing algorithms for language identification.

Is Attention always needed? A case study on language identification from speech

Is Attention always needed? A case study on language identification from speech

Branch-Transformer: A Parallel Branch Architecture to Capture Local and Global Features for Language Identification

Branch-Transformer: A Parallel Branch Architecture to Capture Local and Global Features for Language Identification

CNN-TCN: Deep Hybrid Model Based on Custom CNN with Temporal CNN to Recognize Sign Language

Sign language plays a pivotal role as a primary means of communication for individuals with hearing and speech impairments. Given their limited auditory and vocal communication abilities, these individuals heavily rely on visual cues, such as body language and hand gestures, to convey their emotions and thoughts in everyday social interactions. Sign language primarily consists of characters (letters) and numerals (numbers). This study introduces an innovative hybrid methodology for automated sign language identification, combining Temporal Convolutional Neural Network (TCNN) and a Custom Convolutional Neural Network (CCNN). The effectiveness of this system was rigorously evaluated using three distinct benchmark datasets that encompass isolated letters and digits. These datasets are comprehensive and publicly accessible resources covering both British and American sign languages. The proposed CNN-TCN model comprises various phases, including data collection, preprocessing (involving labeling, normalization, and frame extraction), feature extraction using CCNN, and sequence modeling through TCNN. The experimental results clearly demonstrate the remarkable performance of the proposed system, with accuracy, precision, recall, and F1 scores reaching impressive levels of 95.31%, 94.03%, 93.33%, and 93.56%, respectively, across the three diverse datasets. These outcomes serve as compelling evidence of the CNN-TCN method’s viability and effectiveness in the realm of sign language recognition.

Forced Displacement Situation Awareness with Large Language Models: Ukrainian Refugees in Poland Case Study

We evaluated the utility of the large language model (LLM) ChatGPT to develop situation awareness related to the forced displacement of Ukrainian refugees into Poland. Utilizing text messages derived from the Help for Ukrainians in Poland Telegram message group, we used ChatGPT to translate messages in multiple languages into English and identify message topics and themes. Topics and themes from beginning of the war in Ukraine in 2022 were analyzed and visualized using K-means clustering and word clouds. The language identification and translation capabilities of the LLM were evaluated by two human evaluators and measured using Kappa (0.86) and BLUE scores (0.46) with the LLM performing effectively. We conclude that the ability of LLM using carefully developed language prompts for large data volume analysis with no need for manual human analysis shows promise for humanitarian analytics focused on rapidly identifying potential key trends, needs, and locations of displaced people.

The Origins and Destinations of Captives from the Bight of Biafra, 1807–1843: New Evidence from the Identification of African Names and Languages

ABSTRACT Between 1807 and 1843, British naval officers liberated more than thirty thousand Africans from slave vessels that embarked enslaved people along the Bight of Biafra. Large ledger books display these Liberated Africans’ names, sexes, ages, and other characteristics. The names, many of which are easily recognizable today, provide clues about individuals pulled into the transatlantic trade and reveal a range of experiences that shaped the lives of Africans in the nineteenth century. Connecting the names to ethnolinguistic homelands helps establish a rough place of origin for more than twelve thousand of the individuals. The data underscore the centrality of Igbo-speakers – the major language in the Bight of Biafra hinterland – to the region’s slave trade. Given the representative nature of the ethnolinguistic makeup of the individuals to the broader slave trade from the Bight of Biafra, we use the intended destinations of the captured vessels as a basis for projecting the size and direction of the transatlantic diaspora of Igbo-speakers. Despite their limited cultural impact on African and African-descended regions in the Americas, large numbers of captives from Igbo-speaking communities were sent to almost every plantation society in the New World in the nineteenth century.

Enhancing abusive language detection: A domain-adapted approach leveraging BERT pre-training tasks

The widespread adoption of deep learning approaches in natural language processing is largely attributed to their exceptional performance across diverse tasks. Notably, Transformer-based models, such as BERT, have gained popularity for their remarkable efficacy and their ease of adaptation (via fine-tuning) across various domains. Despite their success, fine-tuning these models for informal language, particularly instances involving offensive expressions, presents a major challenge due to limitations in vocabulary coverage and contextual information for such tasks. To address these challenges, we propose the domain adaptation of the BERT language model for the task of detecting abusive language. Our approach involves constraining the language model with the adaptation and paradigm shift of two default pre-trained tasks, the design of two datasets specifically engineered to support the adapted pre-training tasks, and the proposal of a dynamic weighting loss function. The evaluation of these adapted configurations on six datasets dedicated to abusive language detection reveals promising outcomes, with a significant enhancement observed compared to the base model. Furthermore, our proposed methods yield competitive results when compared to state-of-the-art approaches, establishing a robust and easily trainable model for the effective identification of abusive language.

Hyperseed: Unsupervised Learning With Vector Symbolic Architectures.

Motivated by recent innovations in biologically inspired neuromorphic hardware, this article presents a novel unsupervised machine learning algorithm named Hyperseed that draws on the principles of vector symbolic architectures (VSAs) for fast learning of a topology preserving feature map of unlabeled data. It relies on two major operations of VSA, binding and bundling. The algorithmic part of Hyperseed is expressed within the Fourier holographic reduced representations (FHRR) model, which is specifically suited for implementation on spiking neuromorphic hardware. The two primary contributions of the Hyperseed algorithm are few-shot learning and a learning rule based on single vector operation. These properties are empirically evaluated on synthetic datasets and on illustrative benchmark use cases, IRIS classification, and a language identification task using the n -gram statistics. The results of these experiments confirm the capabilities of Hyperseed and its applications in neuromorphic hardware.

AI Based Identification of Inappropriate Language

Abstract: In the current digital era, the widespread use of online communication has raised the demand for automated systems that can recognize and block hate speech, improper language, and objectionable information. The usefulness of three different machine learning algorithms—Decision Trees, Random Forest, Long Short-Term Memory (LSTM), and others—in determining if a given text contains objectionable language is investigated in this work. While LSTM and represent state-of-the-art deep learning algorithms capable of processing unstructured text input, Random Forest and Decision Trees are standard machine learning techniques that rely on organized feature engineering. This study compares different algorithms in an effort to shed light on their advantages and disadvantages in dealing with the changing demands of online content moderation. Our results show each model's accuracy, precision, recall, and F1-score.

Improved word vector space with ensemble deep learning model for language identification

Improved word vector space with ensemble deep learning model for language identification

Geographic Adaptation of Pretrained Language Models

AbstractWhile pretrained language models (PLMs) have been shown to possess a plethora of linguistic knowledge, the existing body of research has largely neglected extralinguistic knowledge, which is generally difficult to obtain by pretraining on text alone. Here, we contribute to closing this gap by examining geolinguistic knowledge, i.e., knowledge about geographic variation in language. We introduce geoadaptation, an intermediate training step that couples language modeling with geolocation prediction in a multi-task learning setup. We geoadapt four PLMs, covering language groups from three geographic areas, and evaluate them on five different tasks: fine-tuned (i.e., supervised) geolocation prediction, zero-shot (i.e., unsupervised) geolocation prediction, fine-tuned language identification, zero-shot language identification, and zero-shot prediction of dialect features. Geoadaptation is very successful at injecting geolinguistic knowledge into the PLMs: The geoadapted PLMs consistently outperform PLMs adapted using only language modeling (by especially wide margins on zero-shot prediction tasks), and we obtain new state-of-the-art results on two benchmarks for geolocation prediction and language identification. Furthermore, we show that the effectiveness of geoadaptation stems from its ability to geographically retrofit the representation space of the PLMs.