Grzegorz Chrupała

Roger Moore reminds Interspeech audience that speech is not audible text. Text is a technology.

Left to right Charlotte Pouw, Willem Zuidema, Marianne de Heer Kloots, Martijn Bentum, Hosein Mohebbi, Grzegorz Chrupała, Gaofei Shen & Tom Lentz.

And that's the whole team behind the tutorial on interpretability techniques for speech models at IS2025.

Wrap-up of the Interspeech tutorial on interpretability for speech models by @mdhk.net

Come join our tutorial in Rotterdam!

Basque and Catalan don't have an army but they do each have a police force.

Feature attribution is always tricky. We show just how tricky it is for speech models.

interspeech2025.org notifications sent

The notifications are out and we have accepted a record-breaking number of papers! Of the 2332 papers sent for review, 1163 were accepted! Acceptance rate: 49.87%

⚠️ Camera-ready deadline: May 31!
🗓️ Registration opens soon
📨 Subscribe to our newsletter www.interspeech2025.org/newsletter

Maybe it found you, as it's been following you all this time...

Looking forward!

Last week to apply for our PhD position!

Took me a while.

Someone tell them they can use their own domain.

@tilburg-university.bsky.social is on BSky. Let's get them to be more active and actually post something!

Gobineau gave us the term Aryan, which does indeed have a linguistic connection. But it postdates and is distinct from Caucasian.

The use of Caucasian as a racial category is due to Johann Friedrich Blumenbach and based on skull shape and physical appearance. I wasn't aware he or others made any connections to language families at the time. The whole idea of the Indo-European language family came later I believe.

We all agree it's bullshit, but I've just never heard the version of the bullshit that claimed Caucasians speak Indo European languages. Even in the 18th century.

Actual Caucasians mostly speak languages unrelated to Indo-European such as Georgian, Chechen, etc.

What's the connection to language families?

I’m again fucking begging anglo media to stop using „Caucasian” to mean „white” ESPECIALLY in any context involving Russia where oppression of actual Caucasians, as in people from ethnic groups inhabiting the Caucasus, is a real ongoing issue.

We listened to speeches and marched through the streets. There were free fries 🍟. Tilburgers were curious and friendly. Protests are not really a thing in the Netherlands 😁

🟥 Today we #strike! The Dutch govt - w/ support of #CDA & #CU - has chosen to break its promise of structural investments in universities and cut €1B+ from the budget.

Full day of activities: Check out the teach-outs & join the main protest at 12.30, Willemsplein, Tilburg!

@woinactie.bsky.social

My R package is in RopenSci and CRAN!🚨 🚨 🚨 🚨

*pangoling*: Access to Large Language Model Predictions

This package is mostly for psycholinguists who just want to get the predictability or surprisal values of words without too much fuss (and without using […]

[Original post on fediscience.org]

Modern LLMs "speak" hundreds of languages... but do they really?
Multilinguality claims are often based on downstream tasks like QA & MT, while *formal* linguistic competence remains hard to gauge in lots of languages

Meet MultiBLiMP!
(joint work w/ @jumelet.bsky.social & @weissweiler.bsky.social)

I'm now searching for new PhD students who are interested in studying how people's brains understand sequences of images like in comics. So, a mix of comics, cogneuro (EEG), and psycholinguistics (especially syntax/semantics). Please circulate to all who might be interested! tiu.nu/22739

Oh that didn't come across as your main concern. There I'd be inclined to agree.

It is in the sense that I am not aware of a field which doesn't end up paying for publishing in one form or another.

That is the case for some fields only. My colleagues who work in cognitive or neuroscience have to shell out hefty APCs, especially for open access publications.

Journal fields have article processing fees which are in the same ballpark as conference travel.

Speech people! The latest #ISCApad is out:
services.isca-speech.org/iscapad/isca...

With great news: the ISCA medalist 2025 is @rogerkmoore.bsky.social 😍

Super happy for him! Roger was my first post-doc advisor. I'm very much looking forward to handing him the Medal at @interspeech.bsky.social 🥳

I don't know about all. I haven't travelled to the US since the beginning of the first Trump administration and still got to go to plenty of conferences. There's no shortage of events outside the US of A.