Shammur Absar Chowdhury

Conversational AI | Representation Learning | Spoken Language Processing

Shammur.jpg

I am a scientist at Qatar Computing Research Institute. My research interest encompasses multilingual, multimodal, and multiview representation learning.

I specialize 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.

I am currently leading (PI) the QVoice project, which empowers speakers—both native and non-native, children, and adults alike—to learn spoken Arabic, leveraging large multimodal AI models.

I have received numerous awards and grants, including the NVIDIA Academic Hardware Grant for my research in Simulating human language learning capabilities using DNN-based language models, a study that was also conducted as a part of the TRAILs project, funded by PRIN MIUR. As a key contributor to the EU-funded projects SENSEI and PortDial, I developed conversational models adept at understanding human conversation, facilitating automatic summarization and mental health screening.

I authored over 60 peer-reviewed publications in top-tier conferences and journals and played an active role in the research community by organizing shared tasks, challenges, and workshops, as well as serving on the committees of top-tier conferences and special interest groups.

I co-founded the Bangla Language Processing (BNLP) Community and MyVoice, a crowdsourced platform, designed to bridge the gaps between standard and dialectal Arabic resources. I am also maintaining the ArabicSpeech Portal.

latest posts