Echo canceller using error back propagation algorithm

Soumava Kumar Roy; Crefeda Faviola Rodrigues

doi:10.1109/ISCMI.2014.33

Echo canceller using error back propagation algorithm

Soumava Kumar Roy, Crefeda Faviola Rodrigues

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

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.

Original language	English
Title of host publication	Proceedings - 2014 International Conference on Soft Computing and Machine Intelligence, ISCMI 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	98-101
Number of pages	4
ISBN (Electronic)	9781479942312
DOIs	https://doi.org/10.1109/ISCMI.2014.33
Publication status	Published - 02-04-2014
Externally published	Yes
Event	2014 1st International Conference on Soft Computing and Machine Intelligence, ISCMI 2014 - New Delhi, Delhi, India Duration: 26-09-2014 → 27-09-2014

Conference

Conference	2014 1st International Conference on Soft Computing and Machine Intelligence, ISCMI 2014
Country/Territory	India
City	New Delhi, Delhi
Period	26-09-14 → 27-09-14

All Science Journal Classification (ASJC) codes

Computer Science(all)

Access to Document

10.1109/ISCMI.2014.33

Cite this

@inproceedings{d538d1dadaa14756a9d4254ceda5fbcd,

title = "Echo canceller using error back propagation algorithm",

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.",

author = "Roy, {Soumava Kumar} and Rodrigues, {Crefeda Faviola}",

year = "2014",

month = apr,

day = "2",

doi = "10.1109/ISCMI.2014.33",

language = "English",

pages = "98--101",

booktitle = "Proceedings - 2014 International Conference on Soft Computing and Machine Intelligence, ISCMI 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2014 1st International Conference on Soft Computing and Machine Intelligence, ISCMI 2014 ; Conference date: 26-09-2014 Through 27-09-2014",

}

Roy, SK & Rodrigues, CF 2014, Echo canceller using error back propagation algorithm. in Proceedings - 2014 International Conference on Soft Computing and Machine Intelligence, ISCMI 2014., 7079362, Institute of Electrical and Electronics Engineers Inc., pp. 98-101, 2014 1st International Conference on Soft Computing and Machine Intelligence, ISCMI 2014, New Delhi, Delhi, India, 26-09-14. https://doi.org/10.1109/ISCMI.2014.33

Echo canceller using error back propagation algorithm. / Roy, Soumava Kumar; Rodrigues, Crefeda Faviola.

Proceedings - 2014 International Conference on Soft Computing and Machine Intelligence, ISCMI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 98-101 7079362.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Echo canceller using error back propagation algorithm

AU - Roy, Soumava Kumar

AU - Rodrigues, Crefeda Faviola

PY - 2014/4/2

Y1 - 2014/4/2

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84946531005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946531005&partnerID=8YFLogxK

U2 - 10.1109/ISCMI.2014.33

DO - 10.1109/ISCMI.2014.33

M3 - Conference contribution

AN - SCOPUS:84946531005

SP - 98

EP - 101

BT - Proceedings - 2014 International Conference on Soft Computing and Machine Intelligence, ISCMI 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 1st International Conference on Soft Computing and Machine Intelligence, ISCMI 2014

Y2 - 26 September 2014 through 27 September 2014

ER -

Echo canceller using error back propagation algorithm

Abstract

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this