DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION

Amir Ivry; Israel Cohen; Baruch Berdugo

doi:10.1109/ICASSP43922.2022.9746557

DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION

Amir Ivry, Israel Cohen, Baruch Berdugo

Technion-Israel Institute of Technology

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

16 Scopus citations

Abstract

We propose a general framework for adaptation control using deep neural networks (NNs) and apply it to acoustic echo cancellation (AEC). First, the optimal step-size that controls the adaptation is derived offline by solving a constrained nonlinear optimization problem that minimizes the adaptive filter misadjustment. Then, a deep NN is trained to learn the relation between the input data and the optimal step-size. In real-time, the NN infers the optimal step-size from streaming data and feeds it to an NLMS filter for AEC. This data-driven method makes no assumptions on the acoustic setup and is entirely non-parametric. Experiments with 100 h of real and synthetic data show that the proposed method outperforms the competition in echo cancellation, speech distortion, and convergence during both single-talk and double-talk.

Original language	English
Title of host publication	2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	741-745
Number of pages	5
ISBN (Electronic)	9781665405409
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9746557
State	Published - 2022
Externally published	Yes
Event	2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, Singapore Duration: 22 May 2022 → 27 May 2022

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2022-May
ISSN (Print)	1520-6149

Conference

Conference	2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Country/Territory	Singapore
City	Hybrid
Period	22/05/22 → 27/05/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE

Funding

This work was supported by the Pazy Research Foundation.

Funders	Funder number
Pazy Research Foundation

Keywords

Acoustic echo cancellation
adaptation control
deep learning
double-talk
variable step-size

Access to Document

10.1109/ICASSP43922.2022.9746557

Cite this

Ivry, A., Cohen, I., & Berdugo, B. (2022). DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION. In 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings (pp. 741-745). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2022-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP43922.2022.9746557

Ivry, Amir ; Cohen, Israel ; Berdugo, Baruch. / DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION. 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 741-745 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{e85c12b90ead48f5a94c87bc08da3d7d,

title = "DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION",

abstract = "We propose a general framework for adaptation control using deep neural networks (NNs) and apply it to acoustic echo cancellation (AEC). First, the optimal step-size that controls the adaptation is derived offline by solving a constrained nonlinear optimization problem that minimizes the adaptive filter misadjustment. Then, a deep NN is trained to learn the relation between the input data and the optimal step-size. In real-time, the NN infers the optimal step-size from streaming data and feeds it to an NLMS filter for AEC. This data-driven method makes no assumptions on the acoustic setup and is entirely non-parametric. Experiments with 100 h of real and synthetic data show that the proposed method outperforms the competition in echo cancellation, speech distortion, and convergence during both single-talk and double-talk.",

keywords = "Acoustic echo cancellation, adaptation control, deep learning, double-talk, variable step-size",

author = "Amir Ivry and Israel Cohen and Baruch Berdugo",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 ; Conference date: 22-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746557",

language = "אנגלית",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

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

pages = "741--745",

booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",

address = "ארצות הברית",

}

Ivry, A, Cohen, I & Berdugo, B 2022, DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION. in 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2022-May, Institute of Electrical and Electronics Engineers Inc., pp. 741-745, 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Hybrid, Singapore, 22/05/22. https://doi.org/10.1109/ICASSP43922.2022.9746557

DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION. / Ivry, Amir; Cohen, Israel; Berdugo, Baruch.
2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 741-745 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2022-May).

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

TY - GEN

T1 - DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION

AU - Ivry, Amir

AU - Cohen, Israel

AU - Berdugo, Baruch

PY - 2022

Y1 - 2022

N2 - We propose a general framework for adaptation control using deep neural networks (NNs) and apply it to acoustic echo cancellation (AEC). First, the optimal step-size that controls the adaptation is derived offline by solving a constrained nonlinear optimization problem that minimizes the adaptive filter misadjustment. Then, a deep NN is trained to learn the relation between the input data and the optimal step-size. In real-time, the NN infers the optimal step-size from streaming data and feeds it to an NLMS filter for AEC. This data-driven method makes no assumptions on the acoustic setup and is entirely non-parametric. Experiments with 100 h of real and synthetic data show that the proposed method outperforms the competition in echo cancellation, speech distortion, and convergence during both single-talk and double-talk.

AB - We propose a general framework for adaptation control using deep neural networks (NNs) and apply it to acoustic echo cancellation (AEC). First, the optimal step-size that controls the adaptation is derived offline by solving a constrained nonlinear optimization problem that minimizes the adaptive filter misadjustment. Then, a deep NN is trained to learn the relation between the input data and the optimal step-size. In real-time, the NN infers the optimal step-size from streaming data and feeds it to an NLMS filter for AEC. This data-driven method makes no assumptions on the acoustic setup and is entirely non-parametric. Experiments with 100 h of real and synthetic data show that the proposed method outperforms the competition in echo cancellation, speech distortion, and convergence during both single-talk and double-talk.

KW - Acoustic echo cancellation

KW - adaptation control

KW - deep learning

KW - double-talk

KW - variable step-size

UR - http://www.scopus.com/inward/record.url?scp=85126975859&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9746557

DO - 10.1109/ICASSP43922.2022.9746557

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85126975859

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 741

EP - 745

BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022

Y2 - 22 May 2022 through 27 May 2022

ER -

Ivry A, Cohen I, Berdugo B. DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION. In 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 741-745. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP43922.2022.9746557

DEEP ADAPTATION CONTROL FOR ACOUSTIC ECHO CANCELLATION

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this