LightNews
gaofeishen.com
Gaofei Shen
@gaofeishen.com
33 followers 120 following 5 posts
nuclear reactor maintenance
Posts Media Videos Starter Packs
gaofeishen.com
Gaofei Shen @gaofeishen.com · Aug 18
Digital poster boards kinda suck
gaofeishen.com
Gaofei Shen @gaofeishen.com · Jun 13
Come join our tutorial in Rotterdam!
mdhk.net
Marianne de Heer Kloots @mdhk.net · Jun 13
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!
Interpretability Techniques for Speech Models — Tutorial @ Interspeech 2025
interpretingdl.github.io
1 7
gaofeishen.com
Gaofei Shen @gaofeishen.com · May 26
In the paper, we also point out that we are barely scratching the surface of **WHAT** information we should use in feature attribution applications when dealing with these speech classification models.
1 1
gaofeishen.com
Gaofei Shen @gaofeishen.com · May 26
We show that we need to be careful when applying existing feature attribution methods to modern speech classification models based on wav2vec 2.0, since the feature attribution results might not be as reliable as we think.
1 2
gaofeishen.com
Gaofei Shen @gaofeishen.com · May 26
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
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
1 2 11