Authors

Hervé Bredin

Publications 2

Preprint Open access

Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition

Séverin Baroudi, Yanis Labrak, Pierfrancesco Melucci et al. · 2026

Activation steering has proven effective for controlling the behavior of Large Language Models (LLMs) at inference time, but its application to SpeechLLMs remains new, and training-free steering approaches for such models are still largely unexplored. We propose a training-free Contrastive Activation Addition (CAA) pro …

Preprint Open access

SepRQ: Self-Supervised Speech Mixture Representation Learning via Mask-Free, Multi-Scale Source Separation

Séverin Baroudi, Hervé Bredin, Ricard Marxer · 2026

Self-supervised learning (SSL) is standard for speech representation learning, but mainstream models are designed around single-speaker audio, limiting their usefulness in multi-speakers scenarios. We present SepRQ, an open-source SSL framework that replaces masked prediction with a pseudo-source-separation objective o …

Co-authors