🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

New research fuels the debate between cascaded and E2E speech translation! The error propagation is addressed by multiple ASR candidates and HuBERT features to preserve acoustic information lost after ASR. Check the paper by Min et al. (2025) at: arxiv.org/pdf/2502.00377.

ReShape Attention bridges speech & text models without extra parameters. Achieves +8.5% BLEU in translation by leveraging acoustic cues, outperforming cascade/E2E methods. Efficient & scalable. Check the paper by Kano et al. (2025) at: ieeexplore.ieee.org/stamp/stamp.js….

📢 Come and join our group! We offer a fully funded 3-year PhD position: 📔Automatic translation with large multimodal models iecs.unitn.it/education/admi… 📍Full details for application: iecs.unitn.it/education/admi… 📅Deadline May 12, 2025 #NLProc Fondazione Bruno Kessler - FBK

🚀 New shared task at #WMT2025 (co-located with EMNLP 2025 ): Model Compression for Machine Translation! Can you shrink an LLM and keep translation quality high?🔧 Submit by July 3 and push the limits of efficient NLP! 👉 www2.statmt.org/wmt25/model-co… #NLP #ML #LLM #ModelCompression

🚀 Boost rare-phrase translation in speech! Uses **bilingual dictionaries** (e.g., "climate change"→"Klimawandel") to dynamically bias outputs. ✅ **+21%** recall in streaming ST ✅ **+85%** in multimodal LLMs 🔗: arxiv.org/abs/2506.09175

🚀 Boost rare-phrase translation in speech! Uses **bilingual dictionaries** to dynamically bias outputs. ✅ **+21%** recall in streaming ST ✅ **+85%** in multimodal LLMs 🔗: arxiv.org/abs/2506.09175

🚀 AdvST: Adversarial training aligns speech and text distributions without parallel data! Combines adversarial learning + hidden-state swapping to fix length mismatch & boost low-resource speech translation. ieeexplore.ieee.org/document/10888…