Our #PickOfTheWeek by @beomseok_lee_: "Can Speech LLMs Think while Listening?" by @yijenshih, @rdesh26, Chunyang Wu, Wei Zhou, SK Bong, @YasheshGaur, Jay Mahadeokar, Ozlem Kalinli, and Mike Seltzer (2025).
#Speech #SpeechLLM #LLM #SpeechTech #AI
Can we make Speech LLMs actually think as they listen? 👂💭
This fascinating work applies CoT inspired by human “thinking while listening”, training models to find the inflection point when reasoning starts.
📄 http://arxiv.org/abs/2510.07497
LT@FBK 2025: l'evento dedicato alle Language Technologies - con 16 talk, 13 poster e una keynote d'eccezione - ha offerto un ampia panoramica a ricercatrici e ricercatori impegnati nello sviluppo di tecnologie per il linguaggio e la comunicazione.
https://magazine.fbk.eu/it/news/ltfbk-2025-nuove-voci-per-le-tecnologie-del-linguaggio/
Our @mgaido91 now presenting FAMA, the first family of large-scale open-science speech foundation models for English and Italian.
Joint work with the @fbk_stek group.
Data, code and models are publicly available, check all info in the paper:
https://clic2025.unica.it/wp-content/uploads/2025/09/80_main_long.pdf
#lt2025fbk