SelectedWorks - Hanan Al Darmaki

Selected Works of Hanan Al Darmaki

Assistant Professor, Department of Natural Language Processing, MBZUAI

Dr Hanan Al Darmaki is an Assistant Professor in the Natural Language Processing at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).

Biography

Prior to joining MBZUAI, Al Darmaki was an assistant professor in the department of computer science and software engineering at UAE University (UAEU). While completing her Ph.D., she worked as a teaching assistant and lecturer at George Washington University as well as on research projects at Apple Inc. and Amazon Web Services as an intern. Before starting her Ph.D., she worked as a statistical analyst at the Statistics Center-Abu Dhabi (SCAD), and as a network engineer at Dubai Electricity and Water Authority.

Al Darmaki’s works on natural language processing (NLP) and automatic speech recognition (ASR) for low-resource languages. The methods she explores include unsupervised learning, transfer learning, and distant supervision to adapt NLP and ASR models to languages and dialects for which labeled data are scarce or non-existent. This includes studying the regularities in text and speech patterns to discover and map terms across languages or modalities, such as unsupervised dictionary induction, cross-lingual embeddings of speech and text, and unsupervised speech-to-text mapping.

Works
About

×

About Hanan Al Darmaki

Dr Hanan Al Darmaki is an Assistant Professor in the Natural Language Processing at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).

Biography

Prior to joining MBZUAI, Al Darmaki was an assistant professor in the department of computer science and software engineering at UAE University (UAEU). While completing her Ph.D., she worked as a teaching assistant and lecturer at George Washington University as well as on research projects at Apple Inc. and Amazon Web Services as an intern. Before starting her Ph.D., she worked as a statistical analyst at the Statistics Center-Abu Dhabi (SCAD), and as a network engineer at Dubai Electricity and Water Authority.

Al Darmaki’s works on natural language processing (NLP) and automatic speech recognition (ASR) for low-resource languages. The methods she explores include unsupervised learning, transfer learning, and distant supervision to adapt NLP and ASR models to languages and dialects for which labeled data are scarce or non-existent. This includes studying the regularities in text and speech patterns to discover and map terms across languages or modalities, such as unsupervised dictionary induction, cross-lingual embeddings of speech and text, and unsupervised speech-to-text mapping.

Present	Assistant Professor, Mohamed bin Zayed University of Artificial Intelligence ‐ Department of Natural Language Processing
Institution Organization Position Type Position Title Time Period to Options Current Position Affiliate my profile with this Institution

Computer Sciences, Data Science, and Computational Linguistics

natural language processing and and automatic speech recognition

http://orcid.org/0000-0003-1706-1777

Journal Articles (1)

Unsupervised Automatic Speech Recognition: A review (Hanan Aldarmaki, Asad Ullah, Sreepratha Ram, et al.) Speech Communication (2022)

Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all languages of ...

Diacritic Recognition Performance in Arabic ASR (Hanan Aldarmaki and Ahmad Ghannam) Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (2023)

In Arabic text, most vowels are encoded in the form of diacritics that are often omitted, so most speech corpora and ASR models are undiacritized. Text-based diacritization has previously been used to preprocess the input ...

Supervised Acoustic Embeddings And Their Transferability Across Languages (Sreepratha Ram and Hanan Aldarmaki) ICNLSP 2022 - Proceedings of the 5th International Conference on Natural Language and Speech Processing (2022)

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pretraining has been ...

ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus (Ajinkya Kulkarni, Atharva Kulkarni, Sara Abedalmon em Mohammad Shatnawi, et al.) Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (2022)

We present a Classical Arabic Text-to-Speech (ClArTTS) corpus to facilitate the development of end-to-end TTS systems for the Arabic language. The speech is extracted from a LibriVox audiobook, which is then processed, segmented, and manually ...

ArTST: Arabic Text and Speech Transformer (Hawau Olamide Toyin, Amirbek Djanibekov, Ajinkya Kulkarni, et al.) arXiv (2023)

We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is ...

Yet Another Model for Arabic Dialect Identification (Ajinkya Kulkarni and Hanan Al Darmaki) arXiv (2023)

In this paper, we describe a spoken Arabic dialect identification (ADI) model for Arabic that consistently outperforms previously published results on two benchmark datasets: ADI-5 and ADI-17. We explore two architectural variations: ResNet and ECAPA-TDNN, ...

Adapting the adapters for code-switching in multilingual ASR (Atharva Kulkarni, Ajinkya Kulkarni, Miguel Couceiro, et al.) arXiv (2023)

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to improve monolingual performance ...

Handling Realistic Label Noise in BERT Text Classification (Maha Tufail Agro and Hanan Al Darmaki) arXiv (2023)

Label noise refers to errors in training labels caused by cheap data annotation methods, such as web scraping or crowd-sourcing, which can be detrimental to the performance of supervised classifiers. Several methods have been proposed ...