Jorge Iranzo-Sánchez

Speech & Machine Translation | PhD Student @mllpresearch

[Jorge Iranzo-Sánchez @jorirsan]

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 :)

[Jorge Iranzo-Sánchez @jorirsan]

the hotel is nice at least 👍

[Jorge Iranzo-Sánchez @jorirsan]

I'll be at the MT Marathon 2025 in Helsinki tomorrow. Come say hi!

[Jorge Iranzo-Sánchez @jorirsan]

(although I'll unfortunately be unable to attend tomorrow morning due to having my flight delayed and having to stay the night in Amsterdam)

[arXiv Sound @ArxivSound]

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," https://t.co/XGzWLWItzL

[Jorge Iranzo-Sánchez @jorirsan]

Live now!

[Jorge Iranzo-Sánchez @jorirsan]

Findings poster today at Session 10! (16:00-17:30) Go find me at Board 267, Hall 4x! #ACL2025NLP

[Jorge Iranzo-Sánchez @jorirsan]

Just arrived to Viena for ACL! I will present two posters: Our findings article "Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation" and our submission to the SimulST task in @iwslt. Feel free to find me and let's have a chat!
#ACL #ACL2025

[Sara Papi @sarapapi]

🔥 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

[Jorge Iranzo-Sánchez @jorirsan]

and [2] https://t.co/RVSSdmT3eT

[Jorge Iranzo-Sánchez @jorirsan]

Just arrived to Viena for ACL! I will present two posters: Our findings article "Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation" and our submission to the SimulST task in @iwslt. Feel free to find me and let's have a chat!
#ACL #ACL2025

[Jorge Iranzo-Sánchez @jorirsan]

If you want to check them out before the conference, here are the links to the papers ;)
[1] https://t.co/SE9iskpEnX

[Sara Papi @sarapapi]

🚀 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 @huggingface 👇
🔗 https://t.co/14PCvNsuCl

#ASR #ST #OpenScience #MultilingualAI

[Lilian Weng @lilianweng]

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”: https://t.co/21xduoZaAF

[arXiv Sound @ArxivSound]

``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… https://t.co/2U0fLV6PpS

[Jorge Iranzo-Sánchez @jorirsan]

really excited to see what everyone has done for this year tasks ヾ(｡･ω･)ｼ

[Jorge Iranzo-Sánchez @jorirsan]

submission for the IWSLT complete :)

[Jorge Iranzo-Sánchez @jorirsan]

unfortunately didn't have lot of time to build the system but hope it performs well🥹🤞

[arXiv Sound @ArxivSound]

``High-Fidelity Simultaneous Speech-To-Speech Translation,'' Tom Labiausse, Laurent Mazar\'e, Edouard Grave, Patrick P\'erez, Alexandre D\'efossez, Neil Zeghidour, https://t.co/QI4WyzkDHv

[Yusuf Kocyigit @mykocyigit]

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.

https://t.co/4AjY5jSgX8

[Sara Papi @sarapapi]

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 @aclanthology (TACL)! 🎉

The preprint is available here: https://t.co/vumEPkZ7vZ