Joint DNN-Based Multichannel Reduction of Acoustic Echo, Reverberation and Noise - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Joint DNN-Based Multichannel Reduction of Acoustic Echo, Reverberation and Noise

Emmanuel Vincent
Eric Humbert

Résumé

We consider the problem of simultaneous reduction of acoustic echo, reverberation and noise. In real scenarios, these distortion sources may occur simultaneously and reducing them implies combining the corresponding distortion-specific filters. As these filters interact with each other, they must be jointly optimized. We propose to model the target and residual signals after linear echo cancellation and dereverberation using a multichannel Gaussian modeling framework and to jointly represent their spectra by means of a neural network. We develop an iterative block-coordinate ascent algorithm to update all the filters. We evaluate our system on real recordings of acoustic echo, reverberation and noise acquired with a smart speaker in various situations. The proposed approach outperforms in terms of overall distortion a cascade of the individual approaches and a joint reduction approach which does not rely on a spectral model of the target and residual signals.
Fichier principal
Vignette du fichier
bare_jrnl.pdf (5.69 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02372579 , version 1 (20-11-2019)
hal-02372579 , version 2 (12-12-2019)
hal-02372579 , version 3 (19-05-2020)
hal-02372579 , version 4 (27-07-2020)

Identifiants

  • HAL Id : hal-02372579 , version 1

Citer

Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert. Joint DNN-Based Multichannel Reduction of Acoustic Echo, Reverberation and Noise. 2019. ⟨hal-02372579v1⟩
392 Consultations
250 Téléchargements

Partager

Gmail Facebook X LinkedIn More