BLASTER: An Off-Grid Method for Blind and Regularized Acoustic Echoes Retrieval -- with supplementary material - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

BLASTER: An Off-Grid Method for Blind and Regularized Acoustic Echoes Retrieval -- with supplementary material

Abstract

Acoustic echoes retrieval is a research topic that is gaining importance in many speech and audio signal processing applications such as speech enhancement, source separation, dereverberation and room geometry estimation. This work proposes a novel approach to blindly retrieve the off-grid timing of early acoustic echoes from a stereophonic recording of an unknown sound source such as speech. It builds on the recent framework of continuous dictionaries. In contrast with existing methods, the proposed approach does not rely on parameter tuning nor peak picking techniques by working directly in the parameter space of interest. The accuracy and ro-bustness of the method are assessed on challenging simulated setups with varying noise and reverberation levels and are compared to two state-of-the-art methods.
Fichier principal
Vignette du fichier
icassp2020_compMat.pdf (443.44 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02469901 , version 1 (14-02-2020)
hal-02469901 , version 2 (14-02-2020)
hal-02469901 , version 3 (23-09-2020)

Identifiers

  • HAL Id : hal-02469901 , version 3

Cite

Diego Di Carlo, Clément Elvira, Antoine Deleforge, Nancy Bertin, Rémi Gribonval. BLASTER: An Off-Grid Method for Blind and Regularized Acoustic Echoes Retrieval -- with supplementary material. ICASSP 2020 - IEEE International Conference on Acoustic Speech and Signal Processing, IEEE, May 2020, Barcelona, Spain. ⟨hal-02469901v3⟩
323 View
270 Download

Share

Gmail Facebook X LinkedIn More