{"slug": "iiit-bgp-iwslt-2026-systems-for-low-resource-st", "title": "IIIT-BGP IWSLT 2026 Systems for Low-resource ST", "summary": "Researchers from IIIT-BGP presented low-resource Bhojpuri-Hindi speech translation systems at IWSLT 2026, including an end-to-end model combining Wav2Vec2 and NLLB-200 with a lightweight adapter, and a cascaded system using Whisper and NLLB-200 with QE Fusion. The systems address the challenge of translating low-resource languages, achieving improved performance through adapter-based integration and quality estimation.", "body_md": "##### Abstract\n\nWe present low-resource Bhojpuri-Hindi speech translation systems for the IWSLT 2026 shared task, covering both end-to-end and cascaded settings. Our end-to-end model connects a Bhojpuri-finetuned Wav2Vec2 encoder to a pretrained NLLB-200 decoder via a lightweight interconnection adapter that combines learnable layer aggregation, CNN-based temporal compression, and Transformer refinement, with optional LoRA-based decoder adaptation. For our cascaded system, we finetune Whisper for Bhojpuri ASR and NLLB-200 for Hindi MT, and further apply QE Fusion with COMET-Kiwi to improve translation selection from beam candidates.- Anthology ID:\n- 2026.iwslt-1.31\n- Volume:\n[Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)](/volumes/2026.iwslt-1/)- Month:\n- July\n- Year:\n- 2026\n- Address:\n- San Diego, USA (in-person and online)\n- Editors:\n[Elizabeth Salesky](/people/elizabeth-salesky/),[Antonios Anastasopoulos](/people/antonios-anastasopoulos/),[Matteo Negri](/people/matteo-negri/),[Marcello Federico](/people/marcello-federico/)- Venues:\n[IWSLT](/venues/iwslt/)|[WS](/venues/ws/)- SIG:\n[SIGSLT](/sigs/sigslt/)- Publisher:\n- Association for Computational Linguistics\n- Note:\n- Pages:\n- 272–283\n- Language:\n- URL:\n[https://aclanthology.org/2026.iwslt-1.31/](https://aclanthology.org/2026.iwslt-1.31/)- DOI:\n- Cite (ACL):\n- Kaustuk Pratap Singh, Dipanshu ., Vedant Singh, and Kumar Rishu. 2026.\n[IIIT-BGP IWSLT 2026 Systems for Low-resource ST](https://aclanthology.org/2026.iwslt-1.31/). In*Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)*, pages 272–283, San Diego, USA (in-person and online). Association for Computational Linguistics. - Cite (Informal):\n[IIIT-BGP IWSLT 2026 Systems for Low-resource ST](https://aclanthology.org/2026.iwslt-1.31/)(Singh et al., IWSLT 2026)- PDF:\n[https://aclanthology.org/2026.iwslt-1.31.pdf](https://aclanthology.org/2026.iwslt-1.31.pdf)", "url": "https://wpnews.pro/news/iiit-bgp-iwslt-2026-systems-for-low-resource-st", "canonical_source": "https://aclanthology.org/2026.iwslt-1.31/", "published_at": "2026-06-30 00:00:00+00:00", "updated_at": "2026-07-01 10:09:55.163641+00:00", "lang": "en", "topics": ["natural-language-processing", "machine-learning", "large-language-models"], "entities": ["IIIT-BGP", "IWSLT", "Wav2Vec2", "NLLB-200", "Whisper", "COMET-Kiwi", "Kaustuk Pratap Singh", "Kumar Rishu"], "alternates": {"html": "https://wpnews.pro/news/iiit-bgp-iwslt-2026-systems-for-low-resource-st", "markdown": "https://wpnews.pro/news/iiit-bgp-iwslt-2026-systems-for-low-resource-st.md", "text": "https://wpnews.pro/news/iiit-bgp-iwslt-2026-systems-for-low-resource-st.txt", "jsonld": "https://wpnews.pro/news/iiit-bgp-iwslt-2026-systems-for-low-resource-st.jsonld"}}