Search

One of the most significant discussions in forensics is Audio Deepfake, where AI-generated tools are used to clone audio content of people’s voices. Although it was intended to improve people’s lives, attackers utilized it maliciously, compromising the public’s safety. Thus, Machine Learning (ML) and Deep Learning (DL) methods have been developed to detect imitated or synthetically faked voices. However, the developed methods suffered from massive training data or excessive pre-processing. To the author’s best knowledge, Arabic speech has not yet been explored with synthetic fake audio, and it is very limited to the challenged fakeness, which is imitation. This paper proposed a new Audio Deepfake detection method called Arabic-AD based on self-supervised learning techniques to detect both synthetic and imitated voices. Additionally, it contributed to the literature by creating the first synthetic dataset of a single speaker who perfectly speaks Modern Standard Arabic (MSA). Besides, the accent was also considered by collecting Arabic recordings from non-Arabic speakers to evaluate the robustness of Arabic-AD. Three extensive experiments were conducted to measure the proposed method and compare it to well-known benchmarks in the literature. As a result, Arabic-AD outperformed other state-of-the-art methods with the lowest EER rate (0.027%), and high detection accuracy (97%) while avoiding the need for excessive training.

Due to the rapid developments in technology and the sudden expansion of social media use, Dialect Arabic has become an important source of data that needs to be addressed when building Arabic corpora. In this paper, thirty-three Arabic corpora are surveyed to show that despite all of the developments in the literature, Saudi dialect (SD) corpora still need further expansion. This paper contributes to the literature on SD corpora by creating the largest Saudi corpus – the King Saud University Saudi Corpus (KSUSC) – with +1B total words, including +119M SD words. The KSUSC not only is the newest and largest SD corpus but is also diverse, covering 26 domains in text collected from five different sources. This paper also contributes to the literature by developing a new incremental preprocessing system that is used to create relevant lexicons that are then used to clean and normalize the collected data. This incremental system is scalable and can be adapted for different resources and dialects. Moreover, the collection process for building the KSUSC is discussed in detail, and the challenges in collecting SD text with respect to each platform are highlighted. By the end of this paper, different design criteria are proposed and used with the KSUSC to conclude that the resulting corpus can be of great benefit to researchers who are interested in integrating the corpus with their own work or using its resulting lexicons with Saudi-based NLP tasks.

According to the Food and Agriculture Organization, the world production of date fruits is 8,526,218 tons and around 1,302,859 tons in the Kingdom of Saudi Arabia (KSA) in 2018. There are several types of date fruits, and the most common in KSA are Barhi, Khalas, Meneifi, Naboot Saif, and Sullaj. Moreover, there are around five main maturity levels: Immature, Khalal, Khalal with Rutab, Pre-Tamar, and Tamar. Harvesting date fruits is performed according to its maturity level and type, which is a critical decision that significantly affects profit. In this paper, we propose a smart harvesting decision system to estimate date fruits type, maturity level, and weight using computer vision (CV) and deep learning (DL) techniques. The proposed system consists of three sub-systems: Dates maturity estimation system (DMES), type estimation system (DTES), and dates weight estimation system (DWES). We utilized four DL architectures, including ResNet, VGG-19, Inception-V3, and NASNet for both DMES and DTES and support vector machine (SVM) (regression and linear) for DWES. We evaluated the performance of the proposed system using the dataset collected by the Center of Smart Robotics Research. Using multiple performance metrics, DTES achieved maximum performance of 99.175% accuracy, an F1 score of 99.225%, 99.8% average precision, and 99.05% average recall. The maximum performance of DMES was 99.058% accuracy, F1 score of 99.34%, 99.64% average precision, and 99.08% average Recall. DWES achieved a maximum performance of 84.27% using SVM-Linear.