AINEVA is the association of Italian regions and autonomous provinces which include Alps, whose goal is to coordinate efforts that local members play in the prevention and information in the field of snow and avalanches. On a daily basis, AINEVA members compile and make available bulletins of conditions and avalanche forecasts written in Italian. In order to allow their consultation to non-Italian people (e.g. foreign tourists), AINEVA members provide translations of original bulletins into languages such as English, French, German and Slovenian. AINEVA and FBK started a 20-month collaboration at the end of 2009 with the goal of developing a system for the automatic translation of such bulletins into English, French and German.
🇦🇹 I’ll be in Vienna for #ACL2025NLP!
Interested in training a SpeechLLM without a lot of params or data? Come to my poster:
🖼️ Mon, 18:00
Also into Speech Summarization? Join my IWSLT talk in collab with @fbk_mt:
🎤 Fri, 14:00
Happy to chat - come say hi! 😎
Papers in 🧵
Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues, "MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks,"
Our pick of the week by @mgaido91: "WhisperKit: On-device Real-time ASR with Billion-Scale Transformers" by Atila Orhon, Arda Okan, Berkin Durmus, @zachnagengast, and Eduardo Pacheco (ICML 2025)
#speech #speechtech #whisper #ASR #realtime
A couple of weeks before presenting our large-scale speech model compression task at IWSLT, here there is of the first attempts to bring large-scale models to the devices on the edge: https://arxiv.org/pdf/2507.10860... Hope to see more works along this direction!
Our pick of the week by @FBKZhihangXie: "Adversarial Speech-Text Pre-Training for Speech Translation" by Chenxuan Liu, Liping Chen, Weitai Zhang, Xiaoxi Li, Peiwang Tang, Mingjia Yu, Sreyan Ghosh, and Zhongyi Ye (ICASSP 2025)
#speech #speechprocessing #speechtech #translation
🚀 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. https://ieeexplore.ieee.org/document/10888294