Arabic Speech Research Articles

AUTOMATED GESTURE RECOGNITION USING APPLIED LINGUISTICS WITH DATA-DRIVEN DEEP LEARNING FOR ARABIC SPEECH TRANSLATION

Gesture recognition for Arabic speech translation includes developing advanced technologies that correctly translate body and hand movements corresponding to Arabic sign language (ArSL) into spoken Arabic. This leverages machine learning and computer vision techniques in complex systems simulation platforms to scrutinize the gestures utilized in ArSL, detecting mild differences in facial expressions, hand shapes, and movements. Sign Language Recognition (SLR) is paramount in assisting communication for the Deaf and Hard-of-Hearing communities. It includes using vision-based methods and Surface Electromyography (sEMG) signals. The sEMG signal is crucial for recognizing hand gestures and capturing muscular activities in sign language. Researchers have comprehensively shown the capability of EMG signals to approach specific details, mainly in classifying hand gestures. This progression is a stimulating feature in extracting the interpretation and recognition of sign languages and investigating the phonology of signed language. Leveraging machine learning algorithms and signal processing techniques in complex systems simulation platforms, researchers aim to extract relevant traits from the sEMG signals that correspond to different ArSL gestures. This study introduces an Enhanced Dwarf Mongoose Algorithm with a Deep Learning-Driven Arabic Sign Language Detection (EDMODL-ASLD) technique on sEMG data. In the initial phase, the presented EDMODL-ASLD model is subjected to data preprocessing to change the input sEMG data into an attuned format. In the next stage, feature extraction with fractal theories is used to gather relevant and nonredundant data from the EMG window to construct a feature vector. In this study, the absolute envelope (AE), energy (E), root-mean square (RMS), standard deviation (STD), and mean absolute value (MAV) are the five time-domain extracted features for the EMG window observation. Meanwhile, the dilated convolutional long short-term memory (ConvLSTM) technique is used to identify distinct sign languages. To improve the results of the dilated ConvLSTM model, the hyperparameter selection process is executed using the EDMO model. To illustrate the significance of the EDMODL-ASLD technique, a brief experimental validation is made on the Arabic SLR database. The experimental validation of the EDMODL-ASLD technique portrayed a superior accuracy value of 96.47% over recent DL approaches.

The news and structural style in the poem of Ibn Zurayq Al-Baghdadi (La Taathleh)

This research deals with the two styles of news and composition in Ibn Zuraiq Al-Baghdadi’s poem (Do not torture him); These two styles are the pillars of Arabic speech and the basis of its discourse, and each of them has linguistic, grammatical, stylistic, and rhetorical characteristics that distinguish it from the other. In this research, we will discuss the definition of the two styles in language and terminology, and provide a brief overview of the poet mentioned in our research. Then we will move on to mention the declarative places, as well as the constructional ones, and how Ibn Zuraiq al-Baghdadi used them in each place, and the reasons for his use of each style. And exploring the aesthetics of all of the above to conclude a set of results in which we mention the aesthetics of each style in poetic discourse, and the extent of this poet’s ability to employ methods to attract the recipient’s attention towards what he presented. The aim of the study is to highlight the stylistic and rhetorical features of the two styles as well, and to work on analyzing the aforementioned verses, including predicates or constructions. It should be noted that there are verses that contain both styles, so we will analyze the style in which we see the appropriate or strongest significance, even though we have analyzed the two styles in a way that we hope to It will be enough. After that comes the list of sources and references that we have adopted in this research. They are diverse sources and references, including traditional, rhetorical, grammatical, and contextual sources, as well as the books of hadith scholars due to their importance in rhetorical and contextual studies.

Efficient and Robust Arabic Automotive Speech Command Recognition System

The automotive speech recognition field has become an active research topic as it enables drivers to activate various in-car functionalities without being distracted. However, research in Arabic remains nascent compared to English, French, and German. Therefore, this paper presents a Moroccan Arabic automotive speech recognition system. Our system aims to enhance the driving experience to make it comfortable and safe while assisting individuals with disabilities. We created a speech dataset comprising 20 commonly used car commands. It consists of 5600 instances collected from Moroccan contributors and recorded in clean and noisy environments to increase its representativity. We used MFCC, weighted MFCC, and Spectral Subband Centroids (SSC) for feature extraction, as they demonstrated promising results in noisy settings. For classifier construction, we proposed a hybrid architecture, consisting of Bidirectional Long Short-Term Memory (Bi-LSTM) and the Convolutional Neural Network (CNN). Training our proposed model with WMFCC and SSC features achieved an accuracy of 98.48%, outperforming all baseline models we trained and outperforming the existing solutions in the state-of-the-art literature. Moreover, it shows promising results in a clean and noisy environment and maintains resilience to additive Gaussian noise while using few computational resources.

Learning Arabic and the Yellow Book at the Alfahmu Littatahfidz Wata'dib Kampar Islamic Boarding School

The aim of this service is to improve the understanding of Arabic for students at the Alfahmu Littahfidz Watta'dib Kampar Islamic Boarding School. The service method is carried out using the ilqa'ul mufradat method (providing vocabulary), muhadatsah, Arabic speech, and yellow book study. The results of the service show that implementing Arabic language learning activities through several methods can improve the student's ability to speak Arabic and read the Kuing book. Integrated Arabic language learning can increase the active role of students in participating in yellow book reading competitions between sub-districts. Even though they are not yet in the top three categories, the student's ability to learn Arabic has shown a significant increase in both reading competence, listening competence, speaking competence in Arabic, and writing Arabic texts.

LipPrint: Using Lip Movements as a Silent Password

Authentication and confidentiality are critical elements in many systems, and passwords are used to protect these systems. One way to enter the password into the system is via voice. The problem with this type of password is that people listen to it easily. The general purpose of this study was to make the password based on lip movement instead of sound. To address this problem, a visual speech recognition (VSR) system was proposed that detects speech from lip movement as a silent password. The proposed system consists of preprocessing the captured video via the proposed algorithms and feature extraction and classification of spoken digits via a modified VGG16. Fairness, robustness, and privacy are also considered in the proposed system. Research has focused on Arabic digits because there is little research on Arabic visual speech recognition. The reported results of the model show remarkable performance, with a validation accuracy of 96.74%. It was concluded that the proposed system, which relies on analysing lip movement instead of sound, increases security by preventing others from hearing the spoken password.

ArabRecognizer: modern standard Arabic speech recognition inspired by DeepSpeech2 utilizing Franco-Arabic

ArabRecognizer: modern standard Arabic speech recognition inspired by DeepSpeech2 utilizing Franco-Arabic

Code-mixing unveiled: Enhancing the hate speech detection in Arabic dialect tweets using machine learning models.

Technological developments over the past few decades have changed the way people communicate, with platforms like social media and blogs becoming vital channels for international conversation. Even though hate speech is vigorously suppressed on social media, it is still a concern that needs to be constantly recognized and observed. The Arabic language poses particular difficulties in the detection of hate speech, despite the considerable efforts made in this area for English-language social media content. Arabic calls for particular consideration when it comes to hate speech detection because of its many dialects and linguistic nuances. Another degree of complication is added by the widespread practice of "code-mixing," in which users merge various languages smoothly. Recognizing this research vacuum, the study aims to close it by examining how well machine learning models containing variation features can detect hate speech, especially when it comes to Arabic tweets featuring code-mixing. Therefore, the objective of this study is to assess and compare the effectiveness of different features and machine learning models for hate speech detection on Arabic hate speech and code-mixing hate speech datasets. To achieve the objectives, the methodology used includes data collection, data pre-processing, feature extraction, the construction of classification models, and the evaluation of the constructed classification models. The findings from the analysis revealed that the TF-IDF feature, when employed with the SGD model, attained the highest accuracy, reaching 98.21%. Subsequently, these results were contrasted with outcomes from three existing studies, and the proposed method outperformed them, underscoring the significance of the proposed method. Consequently, our study carries practical implications and serves as a foundational exploration in the realm of automated hate speech detection in text.

Разум, язык, культура: как сегодня прочитывать концепцию «арабского разума» ал-Джа̄бири

In his four-volume Critique of Arab Reason the late Moroccan philosopher Muḥammad ‘Ābid al-Jābirī (1935–2010) argues that human history witnessed “Greco-European” and “Arab” variants of reason, and not the single one. He challenges the confidence of philosophers in the universality of reason which disclosed itself in the course of European history. Reading al-Jābirī’s theory in Kantian optics will prove fruitful in view of significant number of observations accumulated in Arabic philosophical studies and directly related to the question of the type of rationality that grounds Arab-Muslim culture. The Arabic linguistic tradition bases itself not on the being of substance but on the flux of action. The indivisible segment of the Arabic speech is the flow of sound between the two “sides” (ḥ arf, pl. ḥ urūf). The copulative function ensures the gluing of the subject and predicate into a single statement due to the action of “leaning” (isnād) between them, which excludes the use of the “to be”-like copula and removes “being” from the list of the fundamental metaphysical categories. All Arabic words, with few exceptions, are “branches” growing from “roots” represented by names of actions. The “root – branches” (’aṣl – furū‘) model, developed by the representatives of the Arabic linguistic tradition and Islamic jurists, explains the diversity of Islamic culture which allows for direct contradictions, legitimizing them by tracing down to a single “root”, which contrasts with the law of contradiction fundamental to European rationality. Islamic ethics is concerned not with the moral perfection of a single substantial individual, but with maintaining a network of interactions between human being and God and between members of society, constituting society not as a hierarchy of strata and classes, but as multiple networks of interactions. The concept of the “Arab reason” by al-Jābirī, read in Kantian optics on the basis of the achievements of philosophical Arabic studies, allows to substantiate the hypothesis of the plurality of types of rationality developed through the history of humankind.

Comparing Pre-trained Language Model for Arabic Hate Speech Detection

Comparing Pre-trained Language Model for Arabic Hate Speech Detection

Cross-modal learning representation using new margin combination for speech recognition task

Cross-modal retrieval aims to elucidate the fusion of information, mimic human learning, and advance the field. The main challenge in cross-modal matching is to build a shared subspace reflecting semantic proximity. Previous works fail to capture asymmetric relevance by adopting symmetric similarity computations. To overcome these shortcomings, an efficient approach called quaternion representation learning (QRL) is introduced for better cross-modal matching. Thus, a better representation of the shared semantics is offered by virtue of its richer representation capacity of the quaternionic space and its strong expressive power. Transfer learning is a crucial aspect in this context. By leveraging pre-trained models, the knowledge gained from one task or domain can be effectively transferred to another, allowing for improved performance and generalization. In this study, transfer learning is employed to enhance the cross-modal retrieval system. Specifically, a pre-trained ResNet-512 model is utilized in conjunction with the proposed total margin (TM) loss function, which combines the QRL approach with the novel adaptive mean margin (AMM) methodology. The TM loss function, coupled with the pre-trained ResNet-512 model, is evaluated on the Audio-Visual Arabic Speech Database (AVAS) and the Arabic Visual Speech Database (AVSD), along with other audio-visual datasets. Experimental results demonstrate the effectiveness of the TM loss function in consistently improving performance on both databases. The recall scores (R@k) and mean average precision (mAP) values achieved on the AVAS Database are as follows: R@1: 42.1±0.7, R@2: 70.2±0.1, R@5: 78.5±1.0, and mAP: 53.0±1.1. Similarly, on the AVSD Database, the results are R@1: 41.7±0.3, R@2: 69.2±1.1, R@5: 78.0±0.3, and mAP: 52.7±0.5. By incorporating transfer learning and the TM loss function into the cross-modal retrieval framework, this study demonstrates the potential for improving clustering efficiency and enhancing visual and speech understanding. The combination of pre-trained models and the TM loss function offers a promising avenue for advancing crossmodal matching techniques and achieving state-of-the-art performance.

Fine-grained hate speech detection in Arabic using transformer-based models

With the proliferation of social media platforms, characterized by features such as anonymity, user-friendly access, and the facilitation of online community building and discourse, the matter of detecting and monitoring hate speech has emerged as an increasingly formidable challenge for society, individuals, and researchers. Despite the crucial importance of hate speech detection task, the majority of work in this field has been conducted in English, with insufficient focus on other languages, particularly Arabic. Furthermore, most existing studies on Arabic hate speech detection have addressed this task as a binary classification problem, which is unreliable. Therefore, the aim of this study is to provide an enhanced model for detecting fine-grained hate speech in Arabic. To this end, three transformer-based models were evaluated to generate contextualized word embeddings from input sequence. Additionally, these models were combined with a bidirectional gated recurrent unit (BiGRU) layer to further improve the extracted semantic and context features. The experiments were conducted on an Arabic reference dataset provided by the open-source Arabic corpora and processing tools (OSACT-5) shared task. A comparative analysis indicates the efficiency of the proposed model over the baseline and related work models by achieving a macro F1-score of 61.68%.

Phonological substitution patterns in Yemeni Ibbi Arabic child speech: a markedness and natural phonology perspective

Phonological substitution patterns in Yemeni Ibbi Arabic child speech: a markedness and natural phonology perspective

Unsupervised phoneme segmentation of continuous Arabic speech

Unsupervised phoneme segmentation of continuous Arabic speech

The Strategies of Persuasion in Political Discourse: A Comparative Analysis of the Political Speeches of Arab and Non-Arab Leaders During Covid-19 Pandemic

This paper investigated the persuasive methods in Arabic and non-Arabic political speeches during the beginning of Covid-19 pandemic, as well as the similarities and differences between Arab and non-Arab leaders in using persuasive strategies. Data of the study consisted of the political speeches which were concerned with the Covid-19 situation in six different countries of the world, released between March and August 2020. The data analysis examines persuasive methods in political speeches and analyze them using Aristotle's triangle (Rhetorical Triangle). The analysis revealed that persuasive strategies based on Aristotle’s theory (400 B.C) were applied in the six leaders’ political speeches during the beginning of Covid-19 pandemic. Moreover, the results indicated that the most frequently persuasive strategies used by the Arab leaders are pathos and ethos strategies. Of the three strategies, it could be observed that logos and ethos strategies were the most employed by non-Arab in their speeches.

Convolutional Neural Networks to Facilitate the Continuous Recognition of Arabic Speech with Independent Speakers

Automatic speech recognition (ASR) is a field of research that focuses on the ability of computers to process and interpret speech feedback from humans and to provide the highest degree of accuracy in recognition. Speech is one of the simplest ways to convey a message in a basic context, and ASR refers to the ability of machines to process and accept speech data from humans with the greatest degree of accuracy. As the human-to-machine interface continues to evolve, speech recognition is expected to become increasingly important. However, the Arabic language has distinct features that set it apart from other languages, such as the dialect and the pronunciation of words. Until now, insufficient attention has been devoted to continuous Arabic speech recognition research for independent speakers with a limited database. This research proposed two techniques for the recognition of Arabic speech. The first uses a combination of convolutional neural network (CNN) and long short-term memory (LSTM) encoders, and an attention-based decoder, and the second is based on the Sphinx-4 recognizer, which includes pocket sphinx, base sphinx, and sphinx train, with various types and number of features to be extracted (filter bank and mel frequency cepstral coefficients (MFCC)) based on the CMU Sphinx tool, which generates a language model for different sentences spoken by different speakers. These approaches were tested on a dataset containing 7 hours of spoken Arabic from 11 Arab countries, covering the Levant, Gulf, and African regions, which make up the Arab world, and achieved promising results. CNN-LSTM achieved a word error rate (WER) of 3.63% using 120 features for filter bank and 4.04% WER using 39 features for MFCC, respectively, while the Sphinx-4 recognizer technique achieved 8.17% WER and an accuracy of 91.83% using 25 features for MFCC and 8 Gaussian mixtures, respectively, when tested on the same benchmark dataset.

Deep Learning for Arabic Speech Recognition Using Convolutional Neural Networks

Extracting the speaker's emotional state from their speech has become an active research topic lately due to the demand for more human interactive applications. This field of research has noted significant advancement, especially in the English language, owing to the availability of massive speech-labeled corpora. However, the progress of analogous methodologies in the Arabic language is still in its infancy stages. In this paper, we present a Speech Recognition model for the Arabic language, proficient in discerning both the emotional state and gender of the speaker through voice analysis. Three primary emotion labels were selected: low, standard, and high levels of emotion. Various spectral features, such as the mel-frequency cepstral coefficient (MFCC), were extracted and tested to determine the optimal features. Furthermore, various Machine Learning models (SVM, KNN, and HMM) and Deep Learning models (LSTM and CNN) were evaluated for training. The results were compared between the five models using different extracted features, ultimately culminating in the selection of MFCC, root-mean-square (RMS), mel-scaled spectrogram, spectral, and zero-crossing rate as spectral features, and the CNN as a classification model. This selection yielded significant results, with an accuracy of 93% for emotion recognition and 99% for gender recognition.

Deep Learning, Ensemble and Supervised Machine Learning for Arabic Speech Emotion Recognition

Today, automatic emotion recognition in speech is one of the most important areas of research in signal processing. Identifying emotional content in Arabic speech is regarded as a very challenging and intricate task due to several obstacles, such as the wide range of cultures and dialects, the influence of cultural factors on emotional expression, and the scarcity of available datasets. This study used a variety of artificial intelligence models, including Xgboost, Adaboost, KNN, DT, and SOM, and a deep-learning model named SERDNN. ANAD was employed as a training dataset, which contains three emotions, "angry", "happy", and "surprised", with 844 features. This study aimed to present a more efficient and accurate technique for recognizing emotions in Arabic speech. Precision, accuracy, recall, and F1-score metrics were utilized to evaluate the effectiveness of the proposed techniques. The results showed that the Xgboost, SOM, and KNN classifiers achieved superior performance in recognizing emotions in Arabic speech. The SERDNN deep learning model outperformed the other techniques, achieving the highest accuracy of 97.40% with a loss rate of 0.1457. Therefore, it can be relied upon and deployed to recognize emotions in Arabic speech.

A systematic literature review of hate speech identification on Arabic Twitter data: research challenges and future directions.

The automatic speech identification in Arabic tweets has generated substantial attention among academics in the fields of text mining and natural language processing (NLP). The quantity of studies done on this subject has experienced significant growth. This study aims to provide an overview of this field by conducting a systematic review of literature that focuses on automatic hate speech identification, particularly in the Arabic language. The goal is to examine the research trends in Arabic hate speech identification and offer guidance to researchers by highlighting the most significant studies published between 2018 and 2023. This systematic study addresses five specific research questions concerning the types of the Arabic language used, hate speech categories, classification techniques, feature engineering techniques, performance metrics, validation methods, existing challenges faced by researchers, and potential future research directions. Through a comprehensive search across nine academic databases, 24 studies that met the predefined inclusion criteria and quality assessment were identified. The review findings revealed the existence of many Arabic linguistic varieties used in hate speech on Twitter, with modern standard Arabic (MSA) being the most prominent. In identification techniques, machine learning categories are the most used technique for Arabic hate speech identification. The result also shows different feature engineering techniques used and indicates that N-gram and CBOW are the most used techniques. F1-score, precision, recall, and accuracy were also identified as the most used performance metric. The review also shows that the most used validation method is the train/test split method. Therefore, the findings of this study can serve as valuable guidance for researchers in enhancing the efficacy of their models in future investigations. Besides, algorithm development, policy rule regulation, community management, and legal and ethical consideration are other real-world applications that can be reaped from this research.

A semantic study of pleonasm in English and Arabic Political Speeches

تهدف هده الورقة البحثية الى دراسة مفهوم الحشو او التكرار في اللغة الانكليزية والذي يعرف بانه تكرار نفس الفكرة من خلال استخدام اثنين او الكثر من الكلمات المتنوعة في نفس الجملة مثل" رأيت بأم عيني" او سمعت بأذاني الخاصة". بيانات هده الدراسة مأخوذة من مقابلتين صحفتين لسياسيين اثنين لغتهم الأم هي الانكليزية والعربية ، احداهما لرئيس الوزراء البريطاني السابق توني بلير في عام 2004 والاخرى لرئيس الوزراء العراقي السابق أياد علاوي كذلك في عام 2004. وخلصت الدراسة الى ان التكرار في الكلمات في النصوص العربية والانكليزية التي تم تحليلها لا لزوم له ولا فائدة منه. ومع ذلك يبدو ان هذه الكلمات ضرورية في بعض الاحيان للتأكيد غلى فكرة معينة او توضيحها اعتمادا على ثقافة المتحدثين ومستقبلي هذه الكلمات. كشف التحليل ايضا ان وجود كلمات زائدة عن الحاجة في خطاب بعض الشخصيات هو مسألة اسلوب وجزء من شخصية المتحدث.

Speech Processing for Arabic Speech Synthesis Based on Concatenation Rules

Speech Processing for Arabic Speech Synthesis Based on Concatenation Rules