Hazem M. Abbas

Mahmoud Selim, Amr Alanwar, M. Watheq El-Kharashi et al.

Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the exploration nature of many RL algorithms, especially when the model of the robot and the environment are unknown. To address this challenge, we propose a data-driven safety layer that acts as a filter for unsafe actions. The safety layer uses a data-driven predictive controller to enforce safety guarantees for RL policies during training and after deployment. The RL agent proposes an action that is verified by computing the data-driven reachability analysis. If there is an intersection between the reachable set of the robot using the proposed action, we call the data-driven predictive controller to find the closest safe action to the proposed unsafe action. The safety layer penalizes the RL agent if the proposed action is unsafe and replaces it with the closest safe one. In the simulation, we show that our method outperforms state-of-the-art safe RL methods on the robotics navigation problem for a Turtlebot 3 in Gazebo and a quadrotor in Unreal Engine 4 (UE4).

Abdullah Abdelfattah, Mahmoud I. Khalil, Hazem Abbas

Assessing spoken language is challenging, and quantifying pronunciation metrics for machine learning models is even harder. However, for the Holy Quran, this task is simplified by the rigorous recitation rules (tajweed) established by Muslim scholars, enabling highly effective assessment. Despite this advantage, the scarcity of high-quality annotated data remains a significant barrier. In this work, we bridge these gaps by introducing: (1) A 98% automated pipeline to produce high-quality Quranic datasets -- encompassing: Collection of recitations from expert reciters, Segmentation at pause points (waqf) using our fine-tuned wav2vec2-BERT model, Transcription of segments, Transcript verification via our novel Tasmeea algorithm; (2) 850+ hours of audio (~300K annotated utterances); (3) A novel ASR-based approach for pronunciation error detection, utilizing our custom Quran Phonetic Script (QPS) to encode Tajweed rules (unlike the IPA standard for Modern Standard Arabic). QPS uses a two-level script: (Phoneme level): Encodes Arabic letters with short/long vowels. (Sifa level): Encodes articulation characteristics of every phoneme. We further include comprehensive modeling with our novel multi-level CTC Model which achieved 0.16% average Phoneme Error Rate (PER) on the testset. We release all code, data, and models as open-source: https://obadx.github.io/prepare-quran-dataset/

Ahmed Zaitoon, Hossam El Din Abd El Munim, Hazem Abbas

The ability to accurately estimate depth information is crucial for many autonomous applications to recognize the surrounded environment and predict the depth of important objects. One of the most recently used techniques is monocular depth estimation where the depth map is inferred from a single image. This paper improves the self-supervised deep learning techniques to perform accurate generalized monocular depth estimation. The main idea is to train the deep model to take into account a sequence of the different frames, each frame is geotagged with its location information. This makes the model able to enhance depth estimation given area semantics. We demonstrate the effectiveness of our model to improve depth estimation results. The model is trained in a realistic environment and the results show improvements in the depth map after adding the location data to the model training phase.

Fady Fahmy, Mahmoud Khalil, Hazem Abbas

Speech synthesis is the artificial production of human speech. A typical text-to-speech system converts a language text into a waveform. There exist many English TTS systems that produce mature, natural, and human-like speech synthesizers. In contrast, other languages, including Arabic, have not been considered until recently. Existing Arabic speech synthesis solutions are slow, of low quality, and the naturalness of synthesized speech is inferior to the English synthesizers. They also lack essential speech key factors such as intonation, stress, and rhythm. Different works were proposed to solve those issues, including the use of concatenative methods such as unit selection or parametric methods. However, they required a lot of laborious work and domain expertise. Another reason for such poor performance of Arabic speech synthesizers is the lack of speech corpora, unlike English that has many publicly available corpora and audiobooks. This work describes how to generate high quality, natural, and human-like Arabic speech using an end-to-end neural deep network architecture. This work uses just $\langle$ text, audio $\rangle$ pairs with a relatively small amount of recorded audio samples with a total of 2.41 hours. It illustrates how to use English character embedding despite using diacritic Arabic characters as input and how to preprocess these audio samples to achieve the best results.

Amr M. Zaki, Mahmoud I. Khalil, Hazem M. Abbas

Text Summarization is the task of condensing long text into just a handful of sentences. Many approaches have been proposed for this task, some of the very first were building statistical models (Extractive Methods) capable of selecting important words and copying them to the output, however these models lacked the ability to paraphrase sentences, as they simply select important words without actually understanding their contexts nor understanding their meaning, here comes the use of Deep Learning based architectures (Abstractive Methods), which effectively tries to understand the meaning of sentences to build meaningful summaries. In this work we discuss one of these new novel approaches which combines curriculum learning with Deep Learning, this model is called Scheduled Sampling. We apply this work to one of the most widely spoken African languages which is the Amharic Language, as we try to enrich the African NLP community with top-notch Deep Learning architectures.

Taha Emara, Hossam E. Abd El Munim, Hazem M. Abbas

Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of accuracy with a little awareness of computational efficiency. In this paper, we introduce LiteSeg, a lightweight architecture for semantic image segmentation. In this work, we explore a new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) and apply short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model. LiteSeg architecture is introduced and tested with multiple backbone networks as Darknet19, MobileNet, and ShuffleNet to provide multiple trade-offs between accuracy and computational cost. The proposed model LiteSeg, with MobileNetV2 as a backbone network, achieves an accuracy of 67.81% mean intersection over union at 161 frames per second with $640 \times 360$ resolution on the Cityscapes dataset.