| 2025 | COLING | Towards Multilingual spoken Visual Question Answering system using Cross-Attention. | Amartya Roy Chowdhury, Tonmoy Rajkhowa, Sanjeev Sharma |
| 2025 | ICASSP | Semi-Supervised Knowledge Distillation Framework towards Lightweight Large Language Model for Spoken Language Translation. | Tonmoy Rajkhowa, Amartya Roy Chowdhury, Achyut Mani Tripathi, Sanjeev Sharma, Om Jee Pandey |
| 2025 | WACV | Bandit-based Attention Mechanism in Vision Transformers. | Amartya Roy Chowdhury, Raghuram Bharadwaj Diddigi, Prabuchandran K. J., Achyut Mani Tripathi |
| 2024 | COLING | Evaluating the Efficacy of Large Acoustic Model for Documenting Non-Orthographic Tribal Languages in India. | Tonmoy Rajkhowa, Amartya Roy Chowdhury, Hrishikesh Ravindra Karande, S. R. Mahadeva Prasanna |
| 2024 | Interspeech | TM-PATHVQA: 90000+ Textless Multilingual Questions for Medical Visual Question Answering. | Tonmoy Rajkhowa, Amartya Roy Chowdhury, Sankalp Nagaonkar, Achyut Mani Tripathi, S. R. Mahadeva Prasanna |
| 2024 | Tencon | Significance of Corpus Quality for Direct Speech-to-Text Translation Systems. | Tonmoy Rajkhowa, Amartya Roy Chowdhury, Lokesh Kumar |