The TOSCA-MP project aimed to develop user-centric content annotation and search tools for professionals in networked media production and archiving (television, radio, online), addressing their specific use cases and workflow requirements. The project brought together 10 partners from 6 European countries including industry partners providing solutions for the media industry, public service broadcasters as well as their European association, a university and research centres. TOSCA-MP investigated scalable and distributed content processing methods performing advanced multimodal information extraction and semantic enrichment. Other key technology areas included search methods across heterogeneous networked content repositories and novel user interfaces. An open standards based service oriented framework integrated the components of the system.
ππΌ Excited to share our work on Speech Foundation Model for data crowdsourcing at COLING 2025 ππΌ
Our co-author Laurent Besacier (@laurent_besacie) at NAVER LABS Europe will be presenting -- don't miss it.
ππΌ Details: https://mt.fbk.eu/1-paper-accepted-at-coling-2025
Exciting news: @iwslt is co-located with #ACL2025NLP again this year! π
Interested in speech processing? Check out the new task on instruction following β any model can participate! π
π
Data release: April 1
β³ Submission deadline: April 15
Donβt miss it! π¬ #NLP #SpeechTech
Weekly pick from the #MeetweenScientificWatch: βVideo-SALMONN: Speech-enhanced audio-visual large language modelsβ β Redefining video comprehension with speech-aware AV-LLMs and groundbreaking QA accuracy. π₯π€π€
Iβm glad to announce that our work βHow "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?β has been accepted at the Transactions of @aclanthology (TACL)! π
The preprint is available here: