Grzegorz Chrupała
@grzegorz.chrupala.me
Reposted by Grzegorz Chrupała
The submission portal for #Interspeech2026 is now open! Submit your papers by 25th February ✍️ interspeech2026.org/en-AU/pages/...
January 16, 2026 at 6:00 AM
The submission portal for #Interspeech2026 is now open! Submit your papers by 25th February ✍️ interspeech2026.org/en-AU/pages/...
Reposted by Grzegorz Chrupała
'Tis the season to preprint BBS commentaries; I'm happy to share ours too! 🎄✨
The textual basis of current LLMs causes trouble, but linguistically relevant insights *can* be found in systems modelling the more natural form of human spoken language: the speech signal itself. arxiv.org/abs/2512.14506
The textual basis of current LLMs causes trouble, but linguistically relevant insights *can* be found in systems modelling the more natural form of human spoken language: the speech signal itself. arxiv.org/abs/2512.14506
December 17, 2025 at 3:22 PM
'Tis the season to preprint BBS commentaries; I'm happy to share ours too! 🎄✨
The textual basis of current LLMs causes trouble, but linguistically relevant insights *can* be found in systems modelling the more natural form of human spoken language: the speech signal itself. arxiv.org/abs/2512.14506
The textual basis of current LLMs causes trouble, but linguistically relevant insights *can* be found in systems modelling the more natural form of human spoken language: the speech signal itself. arxiv.org/abs/2512.14506
If you're in the Netherlands or nearby, check out the Fourth Dutch Speech Tech Day. I'll be there.
www.eventbrite.com/e/4th-dutch-...
www.eventbrite.com/e/4th-dutch-...
4th Dutch Speech Tech Day
We are thrilled to announce that the 4th Dutch Speech Tech Day will take place on Monday, February 2, 2026, at Beeld & Geluid in Hilversum!
www.eventbrite.com
January 13, 2026 at 9:58 AM
If you're in the Netherlands or nearby, check out the Fourth Dutch Speech Tech Day. I'll be there.
www.eventbrite.com/e/4th-dutch-...
www.eventbrite.com/e/4th-dutch-...
Reposted by Grzegorz Chrupała
Big news! 🗞️ I defended my PhD thesis "From Insights to Impact: Actionable Interpretability for Neural Machine Translation" @rug.nl @gronlp.bsky.social
I'm grateful to my advisors @arianna-bis.bsky.social @malvinanissim.bsky.social and to everyone who played a role in this journey! 🎉 #PhDone
I'm grateful to my advisors @arianna-bis.bsky.social @malvinanissim.bsky.social and to everyone who played a role in this journey! 🎉 #PhDone
December 16, 2025 at 12:21 PM
Big news! 🗞️ I defended my PhD thesis "From Insights to Impact: Actionable Interpretability for Neural Machine Translation" @rug.nl @gronlp.bsky.social
I'm grateful to my advisors @arianna-bis.bsky.social @malvinanissim.bsky.social and to everyone who played a role in this journey! 🎉 #PhDone
I'm grateful to my advisors @arianna-bis.bsky.social @malvinanissim.bsky.social and to everyone who played a role in this journey! 🎉 #PhDone
Reposted by Grzegorz Chrupała
Had such a great time presenting our tutorial on Interpretability Techniques for Speech Models at #Interspeech2025! 🔍
For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...
For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...
August 19, 2025 at 9:23 PM
Had such a great time presenting our tutorial on Interpretability Techniques for Speech Models at #Interspeech2025! 🔍
For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...
For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...
Roger Moore reminds Interspeech audience that speech is not audible text. Text is a technology.
August 18, 2025 at 8:18 AM
Roger Moore reminds Interspeech audience that speech is not audible text. Text is a technology.
And that's the whole team behind the tutorial on interpretability techniques for speech models at IS2025.
August 17, 2025 at 7:27 PM
And that's the whole team behind the tutorial on interpretability techniques for speech models at IS2025.
Reposted by Grzegorz Chrupała
Come join our tutorial in Rotterdam!
The @interspeech.bsky.social early registration deadline is coming up in a few days!
Want to learn how to analyze the inner workings of speech processing models? 🔍 Check out the programme for our tutorial:
interpretingdl.github.io/speech-inter... & sign up through the conference registration form!
Want to learn how to analyze the inner workings of speech processing models? 🔍 Check out the programme for our tutorial:
interpretingdl.github.io/speech-inter... & sign up through the conference registration form!
Interpretability Techniques for Speech Models — Tutorial @ Interspeech 2025
interpretingdl.github.io
June 13, 2025 at 5:43 AM
Come join our tutorial in Rotterdam!
Feature attribution is always tricky. We show just how tricky it is for speech models.
I am excited to announce that my paper "On the reliability of feature attribution methods for speech classification" has been accepted to #Interspeech2025!
Co-authors: @hmohebbi.bsky.social, Arianna Bisazza, Afra Alishahi, @grzegorz.chrupala.me
Find the preprint here: arxiv.org/abs/2505.16406
Co-authors: @hmohebbi.bsky.social, Arianna Bisazza, Afra Alishahi, @grzegorz.chrupala.me
Find the preprint here: arxiv.org/abs/2505.16406
On the reliability of feature attribution methods for speech classification
As the capabilities of large-scale pre-trained models evolve, understanding the determinants of their outputs becomes more important. Feature attribution aims to reveal which parts of the input elemen...
arxiv.org
May 26, 2025 at 9:05 AM
Feature attribution is always tricky. We show just how tricky it is for speech models.
Reposted by Grzegorz Chrupała
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
⚠️ Camera-ready deadline: May 31!
🗓️ Registration opens soon
📨 Subscribe to our newsletter www.interspeech2025.org/newsletter
May 20, 2025 at 9:42 AM
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
⚠️ Camera-ready deadline: May 31!
🗓️ Registration opens soon
📨 Subscribe to our newsletter www.interspeech2025.org/newsletter
Looking forward!
Happy to share that in a few weeks ill move to Tilburg University as an Associate Professor at the Department of Cognitive Science and Artificial Intelligence
www.tilburguniversity.edu/about/school... Super excited about this! I want to thank Donders/Radboud and many other people for their support!
www.tilburguniversity.edu/about/school... Super excited about this! I want to thank Donders/Radboud and many other people for their support!
Department of Cognitive Science and Artificial Intelligence | Tilburg University
Members of the Cognitive Science & Artificial Intelligence (CSAI) department conduct research in the interdisciplinary domain of Artificial Intelligence and Cognitive Science and are involved in teach...
www.tilburguniversity.edu
April 17, 2025 at 12:49 PM
Looking forward!
Reposted by Grzegorz Chrupała
Last week to apply for our PhD position!
Apply for our PhD position in language acquisition / computational linguistics in Groningen until 24 April! Job ad is here:
www.rug.nl/about-ug/wor...
www.rug.nl/about-ug/wor...
April 17, 2025 at 9:45 AM
Last week to apply for our PhD position!
Reposted by Grzegorz Chrupała
@tilburg-university.bsky.social is on BSky. Let's get them to be more active and actually post something!
April 14, 2025 at 5:54 AM
@tilburg-university.bsky.social is on BSky. Let's get them to be more active and actually post something!
Reposted by Grzegorz Chrupała
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.
April 10, 2025 at 12:53 PM
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 😁
April 10, 2025 at 6:35 PM
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 😁
Reposted by Grzegorz Chrupała
🟥 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
Full day of activities: Check out the teach-outs & join the main protest at 12.30, Willemsplein, Tilburg!
@woinactie.bsky.social
April 10, 2025 at 5:38 AM
🟥 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
Full day of activities: Check out the teach-outs & join the main protest at 12.30, Willemsplein, Tilburg!
@woinactie.bsky.social
Reposted by Grzegorz Chrupała
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]
*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]
April 9, 2025 at 3:29 PM
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]
*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]
Reposted by Grzegorz Chrupała
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)
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)
✨New paper ✨
Introducing 🌍MultiBLiMP 1.0: A Massively Multilingual Benchmark of Minimal Pairs for Subject-Verb Agreement, covering 101 languages!
We present over 125,000 minimal pairs and evaluate 17 LLMs, finding that support is still lacking for many languages.
🧵⬇️
Introducing 🌍MultiBLiMP 1.0: A Massively Multilingual Benchmark of Minimal Pairs for Subject-Verb Agreement, covering 101 languages!
We present over 125,000 minimal pairs and evaluate 17 LLMs, finding that support is still lacking for many languages.
🧵⬇️
April 8, 2025 at 12:27 PM
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)
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)
Reposted by Grzegorz Chrupała
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
Job opening: Two PhD positions for the neurocognition of the grammar of visual narratives (22739)
tiu.nu
April 7, 2025 at 2:13 PM
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
Reposted by Grzegorz Chrupała
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 🥳
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 🥳
ISCA Services
services.isca-speech.org
March 12, 2025 at 3:27 PM
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 🥳
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 🥳
نوروز مبارک
Happy Nowruz
Happy Nowruz
March 20, 2025 at 9:24 AM
نوروز مبارک
Happy Nowruz
Happy Nowruz
Reposted by Grzegorz Chrupała
📢 #SLaTE2025 – Call for Papers! 🎤📚
🚀 10th Workshop on Speech & Language Technology in Education
📅 Aug 22-24, 2025 | 📍 Radboud Univ., Nijmegen
📝 Special Session: Speak & Improve Challenge 2025
📄 Submit full/short papers
🔗 Info: sites.google.com/view/slate-2...
🚀 10th Workshop on Speech & Language Technology in Education
📅 Aug 22-24, 2025 | 📍 Radboud Univ., Nijmegen
📝 Special Session: Speak & Improve Challenge 2025
📄 Submit full/short papers
🔗 Info: sites.google.com/view/slate-2...
March 18, 2025 at 10:28 AM
📢 #SLaTE2025 – Call for Papers! 🎤📚
🚀 10th Workshop on Speech & Language Technology in Education
📅 Aug 22-24, 2025 | 📍 Radboud Univ., Nijmegen
📝 Special Session: Speak & Improve Challenge 2025
📄 Submit full/short papers
🔗 Info: sites.google.com/view/slate-2...
🚀 10th Workshop on Speech & Language Technology in Education
📅 Aug 22-24, 2025 | 📍 Radboud Univ., Nijmegen
📝 Special Session: Speak & Improve Challenge 2025
📄 Submit full/short papers
🔗 Info: sites.google.com/view/slate-2...
Reposted by Grzegorz Chrupała
u24.gov.ua
Best what one can do as individual is it set a monthly target and donate it until the victory automatically. For example as standing order from your bank using SEPA:
koloua.com/en/donate#sepa
Best what one can do as individual is it set a monthly target and donate it until the victory automatically. For example as standing order from your bank using SEPA:
koloua.com/en/donate#sepa
March 2, 2025 at 11:04 AM
u24.gov.ua
Best what one can do as individual is it set a monthly target and donate it until the victory automatically. For example as standing order from your bank using SEPA:
koloua.com/en/donate#sepa
Best what one can do as individual is it set a monthly target and donate it until the victory automatically. For example as standing order from your bank using SEPA:
koloua.com/en/donate#sepa
Reposted by Grzegorz Chrupała
