The main objectives of the ECHO (European Chronicles on-Line) project are to develop a long-term reusable software infrastructure to support digital film archives, to provide Web-based access to collections of historical documentary films of great international value and to increase the productivity and cost effectiveness of producing digital film archives. The project develops and demonstrates an open architecture approach to distributed digital film archive services. The open architecture will support service extensibility and interoperability. The distinct features of the ECHO system will be semi-automatic metadata extraction and acquisition from digital film information, non-English speech recognizers (Italian, French, Dutch) for the purpose of indexing, searching and retrieval, cross-language retrieval capabilities, intelligent access to digital films, automatic film summary creation, collection mechanisms, privacy and billing mechanisms.
Our pick of the week by @beomseok_lee_: "ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs" by Pooneh Mousavi, @yingzhi_wang, @mirco_ravanelli, and @CemSubakan (2025)
#SLU #speech #multimodal #LLM
Speech-language models show promise in multimodal tasksโbut how well are speech & text actually aligned? ๐ค
This paper https://arxiv.org/abs/2505.19937 proposes a new metric to measure layer-wise correlation between the two, with a focus on SLU tasks. ๐๐ฃ๏ธ๐
๐ Ciao! Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!
๐https://bocconi.eu.qualtrics.com/jfe/form/SV_2nTelXaXvJlinbg (รจ anonimo, dura ~10 m, se partecipi o lo diffondi ci aiuti un sacco๐)
Ci interessa anche raggiungere persone che non si occupano di AI!
Our pick of the week by @apierg: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" by Arjun Subramonian, Vagrant Gautam, Preethi Seshadri, Dietrich Klakow, @kaiwei_chang, @YizhouSun (2025).
#LLM #misgendering #gender
Super interesting paper by Subramonian et al: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" https://arxiv.org/abs/2504.17075
Turns out, misgendering is messier than just pronouns. I'd love to see this analysis extended to grammatical gender languages! #LLM #AI #ethics @fbk_mt
๐ New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in ๐ฌ๐ง English and ๐ฎ๐น Italian.
The models are live and ready to try on @huggingface ๐
๐
#ASR #ST #OpenScience #MultilingualAI