Introducing a nonnative Arabic speech corpus for CAPT: L2AraSpeech
Language Resources and Evaluation · مجلد 60 (3)
Language Resources and Evaluation · مجلد 60 (3)
Sensors · مجلد 25 (17) · 5504-5504
There is a pressing need to build a sign-to-text translation system to simplify communication between deaf and non-deaf people. This study investigates the building of a high-performance, lightweight sign language translation system suitable for real-time applications. Two Saudi Sign Language datasets are used for evaluation. We also investigate the effects of the number of signers and number of repetitions in sign language datasets. To this end, eight experiments are conducted in both signer-dependent and signer-independent modes. A comprehensive ablation study is presented to study the impacts of model components, network depth, and the size of the hidden dimension. The best accuracies achieved are 97.7% and 90.7% for the signer-dependent and signer-independent modes, respectively, using the KSU-SSL dataset. Similarly, the model achieves 98.38% and 96.22% for signer-dependent and signer-independent modes using the ArSL dataset.
Lecture notes in networks and systems · 1-11
Journal of Disability Research · مجلد 4 (6)
Autism spectrum disorder (ASD) is a diverse neurodevelopmental condition with a significant genetic basis. Machine learning (ML) and deep learning (DL) models are emerging as powerful tools for identifying potential ASD risk genes and biomarkers to improve diagnostic accuracy. This narrative systematic review synthesizes evidence on the use of ML and DL models for ASD prediction and diagnosis, focusing on studies that utilized genetic variants and biomarkers. We conducted a systematic search across six databases [Web of Science, PubMed, Science Direct, Semantic Scholar, Institute of Electrical and Electronics Engineers (IEEE Xplore), and Association for Computing Machinery Digital Library (ACM-DL)] for articles published between 2009 and 2024, yielding 483 initial records. Multiple inclusion criteria were applied, and only peer-reviewed articles that used artificial intelligence, ML, or DL to predict ASD based on genetic biomarkers were included. After deduplication and applying inclusion and exclusion criteria, 14 studies were included in this review. These studies focused on genetic variants based on whole-genome sequencing, whole-exome sequencing, RNA sequencing, single-nucleus RNA sequencing, mRNA expression, long non-coding RNA, or single nucleotide polymorphism data. Our findings indicate that various ML models achieved robust performance, while DL architectures such as DeepASDPred outperformed ML models, with an accuracy of 93.8%. Most of the studies used datasets such as the Simons Foundation Autism Research Initiative (SFARI), the Simons Simplex Collection (SSC), the Autism Genetic Resource Exchange (AGRE), Atlas of the Developing Human Brain (BrainSpan), and the Simons Foundation Powering Autism Research for Knowledge (SPARK). The reviewed studies demonstrate that ML can help identify genetic risk factors and biomarkers that contribute to ASD. However, challenges remain, including data heterogeneity, small sample sizes, and the need for greater model interpretability. Addressing these challenges is crucial for translating ML models into clinically useful tools. In conclusion, DL substantially enhances ASD prediction, leveraging genetic data to identify novel candidate genes and support biological discovery of cell type-specific gene expression and roles of non-coding mutations in ASD.
Journal of Computer Science · مجلد 20 (9) · 972-985
This study presents an extensive examination of CPU scheduling algorithms, focusing on the First-Come, First-Served (FCFS), Round-Robin (RR), and Shortest-Job-First (SJF) strategies through a carefully designed scenario-based approach. By deploying a Java-based simulation to dynamically generate random process arrival and burst times, this study simulates a variety of operational conditions to test these scheduling algorithms’ adaptability and performance in environments that closely resemble real-world computing scenarios. The research aims to explore the effects of dynamic quantum size allocation on RR scheduling and assess its impact on system performance metrics such as response time and context switching overhead. Through a detailed analysis, this study seeks to provide new insights into the operational efficiency of the FCFS, RR, and SJF scheduling strategies, highlighting their strengths, limitations, and applicability across different computing environments.
— · مجلد 9 (27)
Arabic Sign Language (ArSL) is a language used by the deaf community across Arab countries, but the lack of familiarity with ArSL among the hearing population often leads to social isolation for deaf individuals. The structural differences between ArSL and spoken Arabic pose significant challenges for machine translation. In this study, we enhance Arabic to ArSL gloss translation by employing data augmentation techniques, expanding the dataset from 600 to over 23,328 samples using sequence-to-sequence transformer models. Our approach achieved a substantial performance improvement, increasing the BLEU score from 11.1% in the baseline model to 52.72% on original test set. The best model achieved a BLEU score of 85.17% on augmented data test, underscoring the effectiveness of data augmentation in enhancing ArSL translation quality.
IEEE Access · مجلد 11 · 135423-135434
Disabled people are facing many difficulties communicating with others and involving in society. Modern societies have dedicated significant efforts to promote the integration of disabled individuals into their societies and services. Currently, smart healthcare systems are used to facilitate disabled people. The objective of this paper is to enable two-way communication of deaf individuals with the rest of society, thus enabling their migration from marginal elements of society to mainstream contributing elements. In the proposed system, we developed three modules; the sign recognition module (SRM) that recognizes the signs of a deaf individual, the speech recognition and synthesis module (SRSM) that processes the speech of a non-deaf individual and converts it to text, and an Avatar module (AM) to generate and perform the corresponding sign of the non-deaf speech, which were integrated into the sign translation companion system called Saudi deaf companion system (SDCS) to facilitate the communication from the deaf to the hearing and vice versa. This paper also contributes to the literature by utilizing our self-developed database, the largest Saudi Sign Language (SSL) database—the King Saud University Saudi-SSL (KSU-SSL). The proposed SDCS system performs 293 Saudi signs that are recommended by the Saudi Association for Hearing Impairment (SAHI) from 10 domains (healthcare, common, alphabets, verbs, pronouns and adverbs, numbers, days, kings, family, and regions).
International Conference on Computing and Information Technology (ICCIT) · 155-159
Computer-Aided Pronunciation Training (CAPT) systems are gaining popularity recently due to the advancements in deep neural networks (DNN) and machine learning and the availability of databases of speech of language learners. Unfortunately, research in Arabic CAPT systems suffer from the lack of CAPT datasets compared to other languages. In this paper, we present the details of and the ideas used in the development of a versatile dataset of speech, real and synthesized, of Arabic Learners. To develop the dataset, we utilized an existing Arabic speech corpus, King Saud University Speech Database (KSU-SD). KSU-SD's main application was a speaker recognition system, but it was designed to be useful in other applications such as CAPT systems. KSU-SD includes a large number of speakers from diverse nationalities (Saudis, Arabs, and Non-Arabs). KSU-SD contains the recording of about 60 non-native speakers from more than 20 nationalities, hence we selected it to build the non-native Arabic-CAPT corpus. The developed corpus consists of transcribed, segmented, and annotated speech, which makes it suitable for building Arabic CAPT systems. In addition to presenting the details of developing the dataset, we also present an analysis of the text and speech errors of the dataset. The dataset was verified by many CAPT systems.