Hanan Aldarmaki

• Ph.D. in computer science from The George Washington University, USA
• Master of Philosophy in computer speech, text, and internet technology (CSTIT) from University of Cambridge, UK
• Bachelor of Science in computer engineering from American University of Sharjah, UAE

Aldarmaki’s current research activities include natural language processing and speech applications for low-resource languages. She also works on developing open-source speech and language models and datasets for the Arabic language and dialects. 

• “ArTST: Arabic Text and Speech Transformer”. Processings of The First Arabic Natural Language Processing Conference (ArabicNLP 2023).
• “ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus”.  Proceedings of INTERSPEECH 2023. 
• “Unsupervised Automatic Speech Recognition: A Review”. Speech Communication, 2022 – Elsevier.
• “Efficient Sentence Embedding using Discrete Cosine Transform”. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP).
• “Scalable Cross-Lingual Transfer of Neural Sentence Embeddings”. Proceedings of the Joint Conference on Lexical and Computational Semantics (*SEM), 2019.
• “Context-Aware Cross-Lingual Mapping”. Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
• “Evaluation of Unsupervised Compositional Representations”. Proceedings of the 27th International Conference on Computational Linguistics (COLING), 2018.
• “Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings”. Transactions Of The Association For Computational Linguistics (TACL), 2018.