JUMAS addresses the need to build an infrastructure able to optimise the information workflow in order to facilitate later analysis. New models and techniques for representing and automatically extracting the embedded semantics derived from multiple data sources will be developed. The most important goal of the JUMAS system is to collect, enrich and share multimedia documents annotated with embedded semantic minimising manual transcription activity. JUMAS is tailored at managing situations in which multiple cameras and audio sources are used to record assemblies in which people debates and event sequences need to be semantically reconstructed for future consultations. The prototype of JUMAS will be tested interworking with legacy systems, but the system can be viewed as able to support business processes and problem-solving in a variety of domains.
Our #PickOfTheWeek by @sarapapi: "RASST: Fast Cross-modal Retrieval-Augmented #Simultaneous #Speech #Translation" by Jiaxuan Luo, @siqi_ouyang, and @lileics (2026).
#RAG #SpeechTech
Very interesting new paper about combining Simultaneous Speech Translation and RAG to improve translation quality! Check it out: https://arxiv.org/pdf/2601.22777
#Speech #SpeechTech #Translation #RAG
Takeaway from our #2 DVPS consortium meeting: scaling with a few modalities won’t unlock the next leap. Progress we need to push in Europe now requires grounding intelligence in interaction and real-time feedback; we’re working on building the most promising MMFM architecture.
Oggi 11 febbraio è la Giornata Internazionale delle Donne e delle Ragazze nella Scienza.
Un’occasione per FBK di condividere e rilanciare il proprio impegno per l’uguaglianza di genere attraverso il Gender Equality Plan 2025-2028, recentemente approvato
https://magazine.fbk.eu/it/news/rinnovato-e-rafforzato-limpegno-verso-luguaglianza-di-genere-in-fbk/
🚀 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗿𝘁𝗶𝗰𝗶𝗽𝗮𝘁𝗶𝗼𝗻: @iwslt Instruction Following 2026
Build general-purpose instruction-following speech models for 🌍 EN/DE/IT/ZH languages!
📅 Eval: 𝗔𝗽𝗿 1 | Submit: 𝗔𝗽𝗿 15
👉
#IWSLT2026 #SpeechAI #MultimodalAI