Low latency auditory attention detection with common spatial pattern analysis of EEG signals

Siqi Cai; Enze Su; Yonghao Song; Longhan Xie; Haizhou Li

doi:10.21437/Interspeech.2020-2496

Low latency auditory attention detection with common spatial pattern analysis of EEG signals

Siqi Cai
, Enze Su
, Yonghao Song
, Longhan Xie
, Haizhou Li

South China University of Technology
National University of Singapore
University of Bremen

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

32 Scopus citations

Abstract

A listener listens to one speech stream at a time in a multi-speaker scenario. EEG-based auditory attention detection (AAD) aims to identify to which speech stream the listener has attended using EEG signals. The performance of linear modeling approaches is limited due to the non-linear nature of the human auditory perception. Furthermore, the real-world applications call for low latency AAD solutions in noisy environments. In this paper, we propose to adopt common spatial pattern (CSP) analysis to enhance the discriminative ability of EEG signals. We study the use of convolutional neural network (CNN) as the non-linear solution. The experiments show that it is possible to decode auditory attention within 2 seconds, with a competitive accuracy of 80.2%, even in noisy acoustic environments. The results are encouraging for brain-computer interfaces, such as hearing aids, which require real-time responses, and robust AAD in complex acoustic environments.

Original language	English
Title of host publication	Interspeech 2020
Publisher	International Speech Communication Association
Pages	2772-2776
Number of pages	5
ISBN (Print)	9781713820697
DOIs	https://doi.org/10.21437/Interspeech.2020-2496
State	Published - 2020
Externally published	Yes
Event	21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China Duration: 25 Oct 2020 → 29 Oct 2020

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2020-October
ISSN (Print)	2308-457X
ISSN (Electronic)	1990-9772

Conference

Conference	21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020
Country/Territory	China
City	Shanghai
Period	25/10/20 → 29/10/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Auditory attention detection (AAD)
Common spatial pattern (CSP)
Convolutional neural networks (CNN)
Electroencephalogram (EEG)

Access to Document

10.21437/Interspeech.2020-2496

Cite this

Cai, S., Su, E., Song, Y., Xie, L., & Li, H. (2020). Low latency auditory attention detection with common spatial pattern analysis of EEG signals. In Interspeech 2020 (pp. 2772-2776). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 2020-October). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2020-2496

@inproceedings{3b2066b772f04e26a61ffd706557e510,

title = "Low latency auditory attention detection with common spatial pattern analysis of EEG signals",

abstract = "A listener listens to one speech stream at a time in a multi-speaker scenario. EEG-based auditory attention detection (AAD) aims to identify to which speech stream the listener has attended using EEG signals. The performance of linear modeling approaches is limited due to the non-linear nature of the human auditory perception. Furthermore, the real-world applications call for low latency AAD solutions in noisy environments. In this paper, we propose to adopt common spatial pattern (CSP) analysis to enhance the discriminative ability of EEG signals. We study the use of convolutional neural network (CNN) as the non-linear solution. The experiments show that it is possible to decode auditory attention within 2 seconds, with a competitive accuracy of 80.2\%, even in noisy acoustic environments. The results are encouraging for brain-computer interfaces, such as hearing aids, which require real-time responses, and robust AAD in complex acoustic environments.",

keywords = "Auditory attention detection (AAD), Common spatial pattern (CSP), Convolutional neural networks (CNN), Electroencephalogram (EEG)",

author = "Siqi Cai and Enze Su and Yonghao Song and Longhan Xie and Haizhou Li",

note = "Publisher Copyright: {\textcopyright} 2020 ISCA; 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",

year = "2020",

doi = "10.21437/Interspeech.2020-2496",

language = "英语",

isbn = "9781713820697",

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

publisher = "International Speech Communication Association",

pages = "2772--2776",

booktitle = "Interspeech 2020",

address = "法国",

}

Cai, S, Su, E, Song, Y, Xie, L & Li, H 2020, Low latency auditory attention detection with common spatial pattern analysis of EEG signals. in Interspeech 2020. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2020-October, International Speech Communication Association, pp. 2772-2776, 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020, Shanghai, China, 25/10/20. https://doi.org/10.21437/Interspeech.2020-2496

Low latency auditory attention detection with common spatial pattern analysis of EEG signals. / Cai, Siqi; Su, Enze; Song, Yonghao et al.
Interspeech 2020. International Speech Communication Association, 2020. p. 2772-2776 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 2020-October).

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

TY - GEN

T1 - Low latency auditory attention detection with common spatial pattern analysis of EEG signals

AU - Cai, Siqi

AU - Su, Enze

AU - Song, Yonghao

AU - Xie, Longhan

AU - Li, Haizhou

PY - 2020

Y1 - 2020

N2 - A listener listens to one speech stream at a time in a multi-speaker scenario. EEG-based auditory attention detection (AAD) aims to identify to which speech stream the listener has attended using EEG signals. The performance of linear modeling approaches is limited due to the non-linear nature of the human auditory perception. Furthermore, the real-world applications call for low latency AAD solutions in noisy environments. In this paper, we propose to adopt common spatial pattern (CSP) analysis to enhance the discriminative ability of EEG signals. We study the use of convolutional neural network (CNN) as the non-linear solution. The experiments show that it is possible to decode auditory attention within 2 seconds, with a competitive accuracy of 80.2%, even in noisy acoustic environments. The results are encouraging for brain-computer interfaces, such as hearing aids, which require real-time responses, and robust AAD in complex acoustic environments.

AB - A listener listens to one speech stream at a time in a multi-speaker scenario. EEG-based auditory attention detection (AAD) aims to identify to which speech stream the listener has attended using EEG signals. The performance of linear modeling approaches is limited due to the non-linear nature of the human auditory perception. Furthermore, the real-world applications call for low latency AAD solutions in noisy environments. In this paper, we propose to adopt common spatial pattern (CSP) analysis to enhance the discriminative ability of EEG signals. We study the use of convolutional neural network (CNN) as the non-linear solution. The experiments show that it is possible to decode auditory attention within 2 seconds, with a competitive accuracy of 80.2%, even in noisy acoustic environments. The results are encouraging for brain-computer interfaces, such as hearing aids, which require real-time responses, and robust AAD in complex acoustic environments.

KW - Auditory attention detection (AAD)

KW - Common spatial pattern (CSP)

KW - Convolutional neural networks (CNN)

KW - Electroencephalogram (EEG)

UR - https://www.scopus.com/pages/publications/85098123660

U2 - 10.21437/Interspeech.2020-2496

DO - 10.21437/Interspeech.2020-2496

M3 - 会议稿件

AN - SCOPUS:85098123660

SN - 9781713820697

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

SP - 2772

EP - 2776

BT - Interspeech 2020

PB - International Speech Communication Association

T2 - 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020

Y2 - 25 October 2020 through 29 October 2020

ER -

Low latency auditory attention detection with common spatial pattern analysis of EEG signals

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this