Our pick of the week by @FBKZhihangXie: "#Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in #SpeechLLMs" by @WangDingdo2603, Junan Li, @HelenMeng_CUHK, et al. (#EMNLP2025)
#SLU #SpeechTech
🚀 New paper: Speech Discrete Tokens or Continuous Features?
📄 https://aclanthology.org/2025.emnlp-main.1266.pdf
🧩 A comprehensive benchmark of SpeechLLMs using HuBERT/WavLM with Qwen & LLaMA.
✨ Continuous features outperform overall, while discrete tokens excel at phoneme-level detail.
🚀 Exciting news from the @FBK_MT group!
Four of our members @BeatriceSavoldi, @lina_conti, @negri_teo & @luisabentivogli are attending #EMNLP2025 in Suzhou 🇨🇳 with 5 accepted papers!
Come to our sessions & let's connect:
🔗 https://mt.fbk.eu/fbk-mt-at-emnlp-2025/
We’re also hiring postdocs!⚡
🎉🎓Congratulations to our PhD student @DennisFucci on a very successful thesis defense! 👏
Many thanks to the evaluation committee members @debora_nozza, @mirco_ravanelli, and Leonardo Badino for their insightful feedback and appreciation of his work!
#nlproc
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