Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation

Chang HAN; Xinmeng XU; Weiping TU; Yuhong YANG; Yajie LIU

doi:10.21437/Interspeech.2023-1364

Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation

Chang HAN
, Xinmeng XU
, Weiping TU^*
, Yuhong YANG
, Yajie LIU

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

3 Citations (Scopus)

Abstract

Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

Original language	English
Title of host publication	24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings
Publisher	International Speech Communication Association
Pages	2443-2447
Number of pages	5
Volume	2023-August
DOIs	https://doi.org/10.21437/Interspeech.2023-1364
Publication status	Published - 2023
Externally published	Yes
Event	24th Annual Conference of the International Speech Communication Association, Interspeech 2023 - Convention Centre Dublin, Dublin, Ireland Duration: 20 Aug 2023 → 24 Aug 2023

Publication series

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

Conference

Conference	24th Annual Conference of the International Speech Communication Association, Interspeech 2023
Country/Territory	Ireland
City	Dublin
Period	20/08/23 → 24/08/23

Bibliographical note

The numerical calculations in this paper have been done on the supercomputing system in the Supercomputing Center of Wuhan University.

Funding

This work was supported in part by the National Nature Science Foundation of China (No. 62071342, No.62171326), the Special Fund of Hubei Luojia Laboratory (No. 220100019), the Hubei Province Technological Innovation Major Project (No. 2021BAA034) and the Fundamental Research Funds for the Central Universities (No.2042023kf1033).

Keywords

acoustic echo cancellation
encoder-decoder architecture
negative information
target positive

Access to Document

10.21437/Interspeech.2023-1364

Cite this

HAN, C., XU, X., TU, W., YANG, Y., & LIU, Y. (2023). Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation. In 24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings (Vol. 2023-August, pp. 2443-2447). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2023-1364

HAN, Chang ; XU, Xinmeng ; TU, Weiping et al. / Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation. 24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings. Vol. 2023-August International Speech Communication Association, 2023. pp. 2443-2447 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{2e5cf654a7ce40c497fdb376c055b694,

title = "Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation",

abstract = "Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.",

keywords = "acoustic echo cancellation, encoder-decoder architecture, negative information, target positive",

author = "Chang HAN and Xinmeng XU and Weiping TU and Yuhong YANG and Yajie LIU",

note = "The numerical calculations in this paper have been done on the supercomputing system in the Supercomputing Center of Wuhan University.; 24th Annual Conference of the International Speech Communication Association, Interspeech 2023 ; Conference date: 20-08-2023 Through 24-08-2023",

year = "2023",

doi = "10.21437/Interspeech.2023-1364",

language = "English",

volume = "2023-August",

series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = "International Speech Communication Association",

pages = "2443--2447",

booktitle = "24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings",

address = "France",

}

HAN, C, XU, X, TU, W, YANG, Y & LIU, Y 2023, Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation. in 24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings. vol. 2023-August, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association, pp. 2443-2447, 24th Annual Conference of the International Speech Communication Association, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1364

Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation. / HAN, Chang; XU, Xinmeng; TU, Weiping et al.
24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings. Vol. 2023-August International Speech Communication Association, 2023. p. 2443-2447 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation

AU - HAN, Chang

AU - XU, Xinmeng

AU - TU, Weiping

AU - YANG, Yuhong

AU - LIU, Yajie

N1 - The numerical calculations in this paper have been done on the supercomputing system in the Supercomputing Center of Wuhan University.

PY - 2023

Y1 - 2023

N2 - Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

AB - Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

KW - acoustic echo cancellation

KW - encoder-decoder architecture

KW - negative information

KW - target positive

UR - https://www.scopus.com/pages/publications/85171559768

U2 - 10.21437/Interspeech.2023-1364

DO - 10.21437/Interspeech.2023-1364

M3 - Conference paper (refereed)

AN - SCOPUS:85171559768

VL - 2023-August

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 2443

EP - 2447

BT - 24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings

PB - International Speech Communication Association

T2 - 24th Annual Conference of the International Speech Communication Association, Interspeech 2023

Y2 - 20 August 2023 through 24 August 2023

ER -

HAN C, XU X, TU W, YANG Y, LIU Y. Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation. In 24th Annual Conference of the International Speech Communication Association, Interspeech 2023: Proceedings. Vol. 2023-August. International Speech Communication Association. 2023. p. 2443-2447. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2023-1364

Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this