Multiple-input neural network-based residual echo suppression - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Multiple-input neural network-based residual echo suppression


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)

Dates and versions

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


  • HAL Id : hal-01723630 , version 2


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⟩
484 View
2606 Download


Gmail Facebook X LinkedIn More