Interspeech paper title: What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
Authors: Marianne de Heer Kloots, Hosein Mohebbi, Charlotte Pouw, Gaofei Shen, Willem Zuidema, Martijn Bentum
β¨ Do self-supervised speech models learn to encode language-specific linguistic features from their training data, or only more language-general acoustic correlates?
At #Interspeech2025 we presented our new Wav2Vec2-NL model and SSL-NL evaluation dataset to test this!
π arxiv.org/abs/2506.00981
β¬οΈ
27.08.2025 14:31 β π 19 π 6 π¬ 1 π 0
Had such a great time presenting our tutorial on Interpretability Techniques for Speech Models at #Interspeech2025! π
For anyone looking for an introduction to the topic, we've now uploaded all materials to the website: interpretingdl.github.io/speech-inter...
19.08.2025 21:23 β π 40 π 14 π¬ 2 π 1
YouTube video by Hosein Mohebbi
Posthoc Disentanglement of Textual and Acoustic Features in Self-Supervised Speech Encoders | AIW'25
Sadly, I couldn't make #ICML2025 in person to present our work at the exciting Actionable Interpretability Workshop @actinterp.bsky.social.
πΊThe recording is online: www.youtube.com/watch?v=QkDF...
+ Poster (on the workshop's website)
πCheck it out and feel free to get in touch for any questions!
17.07.2025 13:52 β π 1 π 0 π¬ 0 π 0
π’ In our #Interspeech2025 tutorial, we'll provide a structured overview of interpretability methods, their applications, challenges, and limitations when applied to spoken language models.
β hands-on experience
interspeech2025.org/tutorials
13.06.2025 13:58 β π 5 π 0 π¬ 0 π 0
Have you already found #BlackboxNLP on Bluesky?π
15.05.2025 18:41 β π 5 π 0 π¬ 0 π 0
π Our Actionable Interpretability workshop has been accepted to #ICML2025! π
> Follow @actinterp.bsky.social
> Website actionable-interpretability.github.io
@talhaklay.bsky.social @anja.re @mariusmosbach.bsky.social @sarah-nlp.bsky.social @iftenney.bsky.social
Paper submission deadline: May 9th!
31.03.2025 16:59 β π 43 π 16 π¬ 3 π 3
My PhD thesis is now available online! It is called "Finding Structure in Language Models" and presents the work I have done in the past 4 years on the intersection of NLP, interpretability, and linguistics.
I'll defend it on December 10, streamed here: jumelet.ai/phd
arxiv.org/abs/2411.16433
π§΅
29.11.2024 15:49 β π 115 π 14 π¬ 8 π 3
The sec. background in (aclanthology.org/2023.emnlp-m...) explains how representations are made in the encoder/decoder of speech transformers.
27.11.2024 08:02 β π 1 π 0 π¬ 0 π 0
ππ»ββοΈ
23.11.2024 23:16 β π 1 π 0 π¬ 0 π 0
Phonologist | asst. prof @ University of Southern California Linguistics | previously: postdoc @ MIT Brain & Cognitive Sciences, PhD @ UCLA Linguistics | theory π experiments π (Bayesian) models | π he | cbreiss.com
Working on dynamic signs and signals in communication at Tilburg University at the Department of Computational Cognitive Science. Interested in language & movement science, complex systems & 4E, Open Science (envisionbox.org) & other things (wimpouw.com)
Professor @SapienzaRoma - Comparative psychology, music neuroscience & bioacoustics. Works on rhythm/sync/speech/communication across species (humans, primates, marine mammals, etc.)
Master's student @ltiatcmu.bsky.social, working on speech AI at @shinjiw.bsky.social
PhD student at ILLC - University of Amsterdam π·
Interested in linguistics and interpretability.
PhD candidate in Trustworthy and Responsible NLP @ Technical University of Munich (TUM)
PhD student in Speech and Hearing at Harvard/MIT. Building ANNs to study how humans perceive/produce speech and voice.
Working with @joshhmcdermott.bsky.social
https://gasserelbanna.github.io/
MSc. at EPFL
BSc. at Cairo University
ex Logitech and IDIAP
Associate Professor and Computational Linguist @ University of Augsburg, Germany
Master student at Saarland university
Assistant professor of computer science at Technion; visiting scholar at @KempnerInst 2025-2026
https://belinkov.com/
The largest workshop on analysing and interpreting neural networks for NLP.
BlackboxNLP will be held at EMNLP 2025 in Suzhou, China
blackboxnlp.github.io
PhD student, NLP Researcher at @cislmu.bsky.social | Prev. Intern @Adobe.com
NLP Graduate Researcher at The University of Tehran #NLProc
#NLP Postdoc at Mila - Quebec AI Institute & McGill University
mariusmosbach.com
Computational linguist trying to understand how humans and computers learn and use language πΆπ§ π£οΈπ₯οΈπ¬
The work is mysterious and important. See https://bbunzeck.github.io
PhDing at @clausebielefeld.bsky.social
Associate Professor at GroNLP ( @gronlp.bsky.social⬠) #NLP | Multilingualism | Interpretability | Language Learning in Humans vs NeuralNets | Mum^2
Head of the InClow research group: https://inclow-lm.github.io/
Postdoctoral researcher at the Institute for Logic, Language and Computation at the University of Amsterdam.
Previously PhD Student at NLPNorth at the IT University of Copenhagen, with internships at AWS, Parameter Lab, Pacmed.
dennisulmer.eu
PhD student in NLP, focusing on low-resource translation with LLMs.
University of Amsterdam
Postdoc at MIT BCS, interested in language(s) in humans and LMs
https://andrea-de-varda.github.io/