Communication Dans Un Congrès Année : 2025

Audio Signal Denoising with Reduced Gaussian Distributions

Résumé

Probabilistic time-frequency representations, though highly promising for signal processing applications, particularly in audio, have been largely overlooked due to their computational complexity and the difficulty in interpreting the underlying models. However, recent research has revealed that these representations can be modeled using Spectral Mixtures Gaussian Processes (SM-GP), which offers a solution to these challenges and enables more tractable and interpretable probabilistic analysis. In this paper, we extend this work by introducing a significant improvement in terms of computational efficiency, flexibility, and real-world applicability. Our approach leverages a recent covariance approximation technique to accelerate SM-GP inference, alongside a frequency-domain method for hyperparameter learning.

Fichier principal
Vignette du fichier
published.pdf (799.44 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05109200 , version 1 (12-06-2025)

Licence

Identifiants

  • HAL Id : hal-05109200 , version 1

Citer

Anis Fradi, Chak Samir, Achref Ouni. Audio Signal Denoising with Reduced Gaussian Distributions. 56ièmes Journées de Statistique de la SFdS, Jun 2025, Marseille, France. ⟨hal-05109200⟩
173 Consultations
107 Téléchargements

Partager

  • More