Mohamed Lazhar Bellagha
Doctorate in Computer Science
About Me
I am a Doctor of Computer Science, specialized in information retrieval in audio data, Natural Language Processing (NLP), and deep learning. My research focuses on speaker identification in Arabic television broadcasts, as well as Automatic Speech Recognition (ASR) for low-resource languages, such as the Tunisian dialect.
Bio
Research Focus Areas
Professional experiences
Education
Scientific publications
Key Research Assets & Open Science Contributions
These initiatives showcase my commitment to developing foundational resources and state-of-the-art models for low-resource Arabic dialects.
TuniSpeech-AI (Hugging Face Organization)
An open research platform dedicated to Tunisian speech and language. It centralizes corpora, recognition models, evaluation benchmarks, and linguistic processing scripts.
TuniSpeech-21h
A multi-genre corpus of 21 hours of Tunisian speech, semi-automatically transcribed and aligned. This resource covers various domains (news, conversation, culture, music, etc.) and serves as a reference base for dialectal ASR research.
Arabic-Word-Embedding Data
A large-scale Arabic corpus compiled from various sources for learning continuous lexical representations. Word vectors (embeddings) were trained and published to support Natural Language Processing (NLP) applications.
Speaker-Role-Recognition
A public dataset and multimodal CNN-LSTM model designed for speaker role recognition in Arabic television news.
TuniSpeech-models
A set of Whisper and Wav2Vec 2.0 models fine-tuned on the TuniSpeech-21h corpus, designed to improve Tunisian speech recognition in diverse acoustic contexts.
TRAINING CERTIFICATE
Scrum Master Certification: by Jim Sullivan
Scrum Methodologies
Learn the foundational knowledge to become proficient with Agile Scrum; Explore User Stories and how they are prioritized in Agile, Velocity, Backlog Refinement, and Market Actions.
Deep Learning Specialization by Younes Bensouda Mourri
Natural Language Processing with Attention Models
Design NLP applications that perform question-answering and sentiment analysis, created tools to translate languages and summarize text, and even built a chatbot
Deep Learning Specialization by Andrew Ng
Structuring Machine Learning Projects
build a successful machine learning project and get to practice decision-making as a machine learning project leader.
Deep Learning Specialization by Andrew Ng
Neural Networks and Deep Learning
build, train, and apply fully connected deep neural networks; implement efficient (vectorized) neural networks; identify key parameters in a neural network’s architecture; and apply deep learning to your own applications.
Deep Learning Specialization by Andrew Ng
Sequence Models
build and train Recurrent Neural Networks (RNNs) and commonly-used variants such as GRUs and LSTMs; apply RNNs to Character-level Language Modeling; gain experience with natural language processing and Word Embeddings; and use HuggingFace tokenizers and transformer models to solve different NLP tasks such as NER and Question Answering.
Deep Learning Specialization by Andrew Ng
Convolutional Neural Networks
build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply these algorithms to a variety of image, video, and other 2D or 3D data.
Machine learning in python with scikit-learn by inria
Machine learning
Deep Learning Specialization by Andrew Ng
Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications; be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning...
