Scholar
Shammur Absar Chowdhury
Google Scholar ID: LkSfdoAAAAAJ
Qatar Computing Research Institute
Citations & Impact
Citations
2,106
H-index
25
i10-index
49
Publications
20
Co-authors
26
list available
Publications
Resume (English only)
Academic Achievements
- Author of over 60 peer-reviewed publications in top-tier conferences and journals. Deeply engaged in the research community through organizing shared tasks, challenges, and workshops, and serving on the committees of leading conferences and special interest groups. Co-founder of the Bangla Language Processing Community and MyVoice, a crowdsourced platform aimed at bridging the gap between standard and dialectal Arabic language resources.
Research Experience
- Research Scientist at Qatar Computing Research Institute (QCRI). Leading the speech technology development in Fanar — QCRI’s Arabic Large Language Model project (sponsored by Qatar Government) — and serves as the Lead PI on both the NAVIA (funded by SRG3) and QVoice projects.
Background
- Research Interest and Expertise: Speech Processing (Representation Learning, Self-Supervised Models, Atypical Human Interaction, Speech Discourse & Turn-taking, and Spoken Language Understanding), Natural Language Processing ((Large) Language Models and their task understanding capabilities, Benchmarking), Explainable and Inclusive Speech Technology (Dialectal and Accented Speech Recognition, Pronunciation Assessment, Children Speech Recognition, Multilingual Models). Short Bio: Dr. Chowdhury specializes in designing Conversational AI models, primarily addressing complex challenges such as multispeaker interactions, nuanced multilingual and dialect variations, and code-switching, among various other intricate conversational dynamics. She is currently leading the speech technology development in Fanar — QCRI’s Arabic Large Language Model project (sponsored by Qatar Government) — and serves as the Lead PI on both the NAVIA (funded by SRG3) and QVoice projects.
Miscellany
- Current Projects: Fanar, AURA, NAVIA, QVoice, LLMeBench. Platforms: BNLP, ArabicSpeech.
