Hosein Mohebbi

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

✨ 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!

📄 arxiv.org/abs/2506.00981

⬇️

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...

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.
📺The recording is online: www.youtube.com/watch?v=QkDF...
+ Poster (on the workshop's website)
👋Check it out and feel free to get in touch for any questions!

📢 In our #Interspeech2025 tutorial, we'll provide a structured overview of interpretability methods, their applications, challenges, and limitations when applied to spoken language models.
➕ hands-on experience
interspeech2025.org/tutorials

Have you already found #BlackboxNLP on Bluesky?🎉

🎉 Our Actionable Interpretability workshop has been accepted to #ICML2025! 🎉
> 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!

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

🧵

The sec. background in (aclanthology.org/2023.emnlp-m...) explains how representations are made in the encoder/decoder of speech transformers.

🙋🏻‍♂️