Multiple-input neural network-based residual echo suppression - Archive ouverte HAL Access content directly
Conference Papers Year :

Multiple-input neural network-based residual echo suppression

(1, 2) , (1) , (1) , (2)
1
2

Abstract

A residual echo suppressor (RES) aims to suppress the residual echo in the output of an acoustic echo canceler (AEC). Spectral-based RES approaches typically estimate the magnitude spectra of the near-end speech and the residual echo from a single input, that is either the far-end speech or the echo computed by the AEC, and derive the RES filter coefficients accordingly. These single inputs do not always suffice to discriminate the near-end speech from the remaining echo. In this paper, we propose a neural network-based approach that directly estimates the RES filter coefficients from multiple inputs, including the AEC output, the far-end speech, and/or the echo computed by the AEC. We evaluate our system on real recordings of acoustic echo and near-end speech acquired in various situations with a smart speaker. We compare it to two single-input spectral-based approaches in terms of echo reduction and near-end speech distortion.
Fichier principal
Vignette du fichier
CARBAJAL_ICASSP_2018.pdf (236.17 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01723630 , version 1 (05-03-2018)
hal-01723630 , version 2 (26-03-2018)

Identifiers

  • HAL Id : hal-01723630 , version 2

Cite

Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert. Multiple-input neural network-based residual echo suppression. ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Canada. pp.1-5. ⟨hal-01723630v2⟩
463 View
2476 Download

Share

Gmail Facebook Twitter LinkedIn More