Decoding Auditory Attention From EEG Data Using Cepstral Analysis
(2023) 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023 In ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings- Abstract
Recent studies of selective auditory attention have demonstrated that neural responses recorded with electroencephalogram (EEG) can be decoded to classify the attended talker in everyday multitalker cocktail-party environments. This is generally referred to as the auditory attention decoding (AAD) and could lead to a breakthrough for the next-generation of hearing aids (HAs) to have the ability to be cognitively controlled. The aim of this paper is to investigate whether cepstral analysis can be used as a more robust mapping between speech and EEG. Our preliminary analysis revealed an average AAD accuracy of 96%. Moreover, we observed a significant increase in auditory attention classification accuracies with our approach over the use... (More)
Recent studies of selective auditory attention have demonstrated that neural responses recorded with electroencephalogram (EEG) can be decoded to classify the attended talker in everyday multitalker cocktail-party environments. This is generally referred to as the auditory attention decoding (AAD) and could lead to a breakthrough for the next-generation of hearing aids (HAs) to have the ability to be cognitively controlled. The aim of this paper is to investigate whether cepstral analysis can be used as a more robust mapping between speech and EEG. Our preliminary analysis revealed an average AAD accuracy of 96%. Moreover, we observed a significant increase in auditory attention classification accuracies with our approach over the use of traditional AAD methods (7% absolute increase). Overall, our exploratory study could open a new avenue for developing new AAD methods to further advance hearing technology. We recognize that additional research is needed to elucidate the full potential of cepstral analysis for AAD.
(Less)
- author
- Alickovic, Emina ; Mendoza, Carlos Francisco ; Segar, Andrew ; Sandsten, Maria LU and Skoglund, Martin A.
- organization
-
- LU Profile Area: Light and Materials
- LU Profile Area: Natural and Artificial Cognition
- LTH Profile Area: Nanoscience and Semiconductor Technology
- LTH Profile Area: AI and Digitalization
- LTH Profile Area: Engineering Health
- NanoLund: Centre for Nanoscience
- eSSENCE: The e-Science Collaboration
- Statistical Signal Processing Group (research group)
- Mathematical Statistics
- Engineering Mathematics (M.Sc.Eng.)
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- auditory attention decoding, cepstral analysis, EEG, speech processing, stimulus reconstruction
- host publication
- ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings
- series title
- ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023
- conference location
- Rhodes Island, Greece
- conference dates
- 2023-06-04 - 2023-06-10
- external identifiers
-
- scopus:85168242810
- ISBN
- 9798350302615
- DOI
- 10.1109/ICASSPW59220.2023.10193192
- language
- English
- LU publication?
- yes
- id
- 5e3ceb82-71c2-48fc-9209-6ee86e7c1ea1
- date added to LUP
- 2023-12-01 14:11:41
- date last changed
- 2023-12-04 07:27:35
@inproceedings{5e3ceb82-71c2-48fc-9209-6ee86e7c1ea1,
abstract = {{<p>Recent studies of selective auditory attention have demonstrated that neural responses recorded with electroencephalogram (EEG) can be decoded to classify the attended talker in everyday multitalker cocktail-party environments. This is generally referred to as the auditory attention decoding (AAD) and could lead to a breakthrough for the next-generation of hearing aids (HAs) to have the ability to be cognitively controlled. The aim of this paper is to investigate whether cepstral analysis can be used as a more robust mapping between speech and EEG. Our preliminary analysis revealed an average AAD accuracy of 96%. Moreover, we observed a significant increase in auditory attention classification accuracies with our approach over the use of traditional AAD methods (7% absolute increase). Overall, our exploratory study could open a new avenue for developing new AAD methods to further advance hearing technology. We recognize that additional research is needed to elucidate the full potential of cepstral analysis for AAD.</p>}},
author = {{Alickovic, Emina and Mendoza, Carlos Francisco and Segar, Andrew and Sandsten, Maria and Skoglund, Martin A.}},
booktitle = {{ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings}},
isbn = {{9798350302615}},
keywords = {{auditory attention decoding; cepstral analysis; EEG; speech processing; stimulus reconstruction}},
language = {{eng}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings}},
title = {{Decoding Auditory Attention From EEG Data Using Cepstral Analysis}},
url = {{http://dx.doi.org/10.1109/ICASSPW59220.2023.10193192}},
doi = {{10.1109/ICASSPW59220.2023.10193192}},
year = {{2023}},
}