Jorge Iranzo-Sánchez (@jorirsan) 's Twitter Profile
Jorge Iranzo-Sánchez

@jorirsan

Speech & Machine Translation | PhD Student @mllpresearch

ID: 1739122849363685376

calendar_today25-12-2023 03:16:20

66 Tweet

24 Takipçi

136 Takip Edilen

Sara Papi (@sarapapi) 's Twitter Profile Photo

I’m glad to announce that our work “How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?” has been accepted at the Transactions of ACL Anthology (TACL)! 🎉 The preprint is available here: arxiv.org/abs/2412.18495

arXiv Sound (@arxivsound) 's Twitter Profile Photo

``High-Fidelity Simultaneous Speech-To-Speech Translation,'' Tom Labiausse, Laurent Mazar\'e, Edouard Grave, Patrick P\'erez, Alexandre D\'efossez, Neil Zeghidour, ift.tt/OEpvThy

Yusuf Kocyigit (@mykocyigit) 's Twitter Profile Photo

Thrilled to share our latest findings on data contamination, from my internship at Google! We trained almost 90 Models on 1B and 8B scales with various contamination types using machine translation as our task and analyze the impact of contamination. arxiv.org/abs/2501.18771

arXiv Sound (@arxivsound) 's Twitter Profile Photo

``BLAB: Brutally Long Audio Bench,'' Orevaoghene Ahia, Martijn Bartelds, Kabir Ahuja, Hila Gonen, Valentin Hofmann, Siddhant Arora, Shuyue Stella Li, Vishal Puttagunta, Mofetoluwa Adeyemi, Charishma Buchireddy, Ben Walls, Noah Bennett, Shinji Watanabe, N… ift.tt/MbhiCOa

Lilian Weng (@lilianweng) 's Twitter Profile Photo

Giving your models more time to think before prediction, like via smart decoding, chain-of-thoughts reasoning, latent thoughts, etc, turns out to be quite effective for unblocking the next level of intelligence. New post is here :) “Why we think”: lilianweng.github.io/posts/2025-05-…

Sara Papi (@sarapapi) 's Twitter Profile Photo

🚀 New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in 🇬🇧 English and 🇮🇹 Italian. The models are live and ready to try on Hugging Face 👇 🔗 huggingface.co/collections/FB… #ASR #ST #OpenScience #MultilingualAI

Sara Papi (@sarapapi) 's Twitter Profile Photo

🔥 Is your real-time SimulST system REAL? Our TACL paper analyzes 110 works and reveals: 🚫 Overreliance on short-form speech 🌀 Terminology chaos 📉 Real-world deployment gaps We bring order-New taxonomy, trends & recommendations! 📍#ACL2025 Poster: Monday 11-12:30, Hall 4/5

🔥 Is your real-time SimulST system REAL?

Our TACL paper analyzes 110 works and reveals: 
🚫 Overreliance on short-form speech 
🌀 Terminology chaos 
📉 Real-world deployment gaps
We bring order-New taxonomy, trends & recommendations!
📍#ACL2025 Poster: Monday 11-12:30, Hall 4/5
arXiv Sound (@arxivsound) 's Twitter Profile Photo

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," arxiv.org/abs/2507.19634

Jorge Iranzo-Sánchez (@jorirsan) 's Twitter Profile Photo

Had lots of fun meeting and talking with everyone this last few days at the MT Marathon in Helsinki!!! Wish everyone a safe trip back home :)