Nonlinear Residual Echo Suppression using a Recurrent Neural Network

Lukas Pfeifenberger, Franz Pernkopf

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


The acoustic front-end of hands-free communication devices introduces a variety of distortions to the linear echo path between the loudspeaker and the microphone. While the amplifiers may introduce a memory-less non-linearity, mechanical vibrations transmitted from the loudspeaker to the microphone via the housing of the device introduce non-linarities with memory, which are much harder to compensate. These distortions significantly limit the performance of linear Acoustic Echo Cancellation (AEC) algorithms. While there already exists a wide range of Residual Echo Suppressor (RES) techniques for individual use cases, our contribution specifically aims at a low-resource implementation that is also real-time capable. The proposed approach is based on a small Recurrent Neural Network (RNN) which adds memory to the residual echo suppressor, enabling it to compensate both types of non-linear distortions. We evaluate the performance of our system in terms of Echo Return Loss Enhancement (ERLE), Signal to Distortion Ratio (SDR) and Word Error Rate (WER), obtained during realistic double-talk situations. Further, we compare the postfilter against a state-of-the art implementation. Finally, we analyze the numerical complexity of the overall system.

Original languageEnglish
Title of host publicationInterspeech 2020
PublisherISCA, International Speech Communication Association
Number of pages5
Publication statusPublished - 1 Jan 2020
Event21st Annual Conference of the International Speech Communication Association: INTERSPEECH 2020 - Shanghai, Virtual, China
Duration: 25 Oct 202029 Oct 2020

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISSN (Print)2308-457X


Conference21st Annual Conference of the International Speech Communication Association
Abbreviated titleInterspeech 2020
CityShanghai, Virtual


  • Acoustic echo cancellation
  • Non-linear echo
  • Recurrent neural networks
  • Residual echo suppression

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Language and Linguistics
  • Human-Computer Interaction
  • Modelling and Simulation


Dive into the research topics of 'Nonlinear Residual Echo Suppression using a Recurrent Neural Network'. Together they form a unique fingerprint.

Cite this