Echo Canceller Using Error Back Propagation Algorithm

Author

Roy, Soumava Kumar ; Rodrigues, Crefeda Faviola

Author_Institution

Dept. of Electron. & Commun, Manipal Inst. of Technol., Manipal, India

fYear

2014

Firstpage

98

Lastpage

101

Abstract

This paper presents the use of Error Back Propagation Algorithm for Adaptive Filter Applications. The Artificial Neural Network (ANN) exploits correlation between the pure speech signal and echo corrupted signal, to generate an estimate of the echo, which in turn subtracts the noise from the echo corrupted signal. Training of ANN is performed using the offline recordings of male and female voice data. Based on the analysis of the recovered pure signal, plots of Signal to Noise Ratio (SNR) vs. Error, Tracking of Weights, Tracking of Echo, Tracking of Error and Variance of Echo with relation to Error has also been shown.

Keywords

adaptive filters; backpropagation; echo suppression; neural nets; speech processing; ANN training; adaptive filter applications; artificial neural network; echo canceller; echo corrupted signal; echo tracking; echo variance; error back propagation algorithm; error tracking; offline female voice data recording; offline male voice data recording; signal to noise ratio; speech signal; weight tracking; Artificial neural networks; Echo cancellers; Neurons; Signal to noise ratio; Speech; Training; Adaptive Filter; Artificial Neural Network (ANN); Audacity; Error Back Propagation Training; Signal to Noise Ratio (SNR);

fLanguage

English

Publisher

ieee

Conference_Titel

Soft Computing and Machine Intelligence (ISCMI), 2014 International Conference on

Type

conf

DOI

10.1109/ISCMI.2014.33

Filename

7079362