Search Results for author: Louis Bahrman

Found 2 papers, 1 papers with code

A Hybrid Model for Weakly-Supervised Speech Dereverberation

no code implementations6 Feb 2025 Louis Bahrman, Mathieu Fontaine, Gael Richard

This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech.

model Speech Dereverberation

Signal Inpainting from Fourier Magnitudes

1 code implementation28 Oct 2022 Louis Bahrman, Marina Krémé, Paul Magron, Antoine Deleforge

Signal inpainting is the task of restoring degraded or missing samples in a signal.

Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.