Yassine El Kheir
@yelkheir.bsky.social
I am a PhD student at the German Research Center for Artificial Intelligence (DFKI) supervised by Prof. Sebastian Möller.
My research focuses on speech deepfake detection, exploring robust, efficient, and explainable methods.
My research focuses on speech deepfake detection, exploring robust, efficient, and explainable methods.
Reposted by Yassine El Kheir
Our pick of the week by @dennisfucci.bsky.social: "Speech Representation Analysis Based on Inter- and Intra-Model Similarities" by @yelkheir.bsky.social, @ratedali.bsky.social, and Shammur Absar Chowdhury (ICASSP Workshops 2024)
Findings from ieeexplore.ieee.org/document/106... show that speech SSL models converge on similar embedding spaces, but via different routes. While overall representations align, individual neurons learn distinct localized concepts.
Interesting read! @fbk-mt.bsky.social
Interesting read! @fbk-mt.bsky.social
Speech Representation Analysis Based on Inter- and Intra-Model Similarities
Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are sti...
ieeexplore.ieee.org
June 20, 2025 at 8:15 AM
Our pick of the week by @dennisfucci.bsky.social: "Speech Representation Analysis Based on Inter- and Intra-Model Similarities" by @yelkheir.bsky.social, @ratedali.bsky.social, and Shammur Absar Chowdhury (ICASSP Workshops 2024)