Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Using Ear-EEG to Decode Auditory Attention in Multiple-speaker Environment

Haolin Zhu, Yujie Yan, Xiran Xu, Zhongshu Ge, Pei Tian, Xihong Wu, Jing Chen

Abstract

Auditory Attention Decoding (AAD) can help to determine the identity of the attended speaker during an auditory selective attention task, by analyzing and processing measurements of electroencephalography (EEG) data. Most studies on AAD are based on scalp-EEG signals in two-speaker scenarios, which are far from real application. Ear-EEG has recently gained significant attention due to its motion tolerance and invisibility during data acquisition, making it easy to incorporate with other devices for applications. In this work, participants selectively attended to one of the four spatially separated speakers' speech in an anechoic room. The EEG data were concurrently collected from a scalp-EEG system and an ear-EEG system (cEEGrids). Temporal response functions (TRFs) and stimulus reconstruction (SR) were utilized using ear-EEG data. Results showed that the attended speech TRFs were stronger than each unattended speech and decoding accuracy was 41.3\% in the 60s (chance level of 25\%). To further investigate the impact of electrode placement and quantity, SR was utilized in both scalp-EEG and ear-EEG, revealing that while the number of electrodes had a minor effect, their positioning had a significant influence on the decoding accuracy. One kind of auditory spatial attention detection (ASAD) method, STAnet, was testified with this ear-EEG database, resulting in 93.1% in 1-second decoding window. The implementation code and database for our work are available on GitHub: https://github.com/zhl486/Ear_EEG_code.git and Zenodo: https://zenodo.org/records/10803261.

Using Ear-EEG to Decode Auditory Attention in Multiple-speaker Environment

Abstract

Auditory Attention Decoding (AAD) can help to determine the identity of the attended speaker during an auditory selective attention task, by analyzing and processing measurements of electroencephalography (EEG) data. Most studies on AAD are based on scalp-EEG signals in two-speaker scenarios, which are far from real application. Ear-EEG has recently gained significant attention due to its motion tolerance and invisibility during data acquisition, making it easy to incorporate with other devices for applications. In this work, participants selectively attended to one of the four spatially separated speakers' speech in an anechoic room. The EEG data were concurrently collected from a scalp-EEG system and an ear-EEG system (cEEGrids). Temporal response functions (TRFs) and stimulus reconstruction (SR) were utilized using ear-EEG data. Results showed that the attended speech TRFs were stronger than each unattended speech and decoding accuracy was 41.3\% in the 60s (chance level of 25\%). To further investigate the impact of electrode placement and quantity, SR was utilized in both scalp-EEG and ear-EEG, revealing that while the number of electrodes had a minor effect, their positioning had a significant influence on the decoding accuracy. One kind of auditory spatial attention detection (ASAD) method, STAnet, was testified with this ear-EEG database, resulting in 93.1% in 1-second decoding window. The implementation code and database for our work are available on GitHub: https://github.com/zhl486/Ear_EEG_code.git and Zenodo: https://zenodo.org/records/10803261.
Paper Structure (14 sections, 2 equations, 4 figures)

This paper contains 14 sections, 2 equations, 4 figures.

Table of Contents

  1. Introduction
  2. METHODS
  3. Subjects
  4. Stimuli and experimental procedure
  5. EEG data acquisition and preprocessing
  6. TRFs estimation
  7. Speech stimulus reconstruction
  8. ASAD
  9. RESULTS AND DISCUSSION
  10. TRFs estimation
  11. Stimulus reconstruction
  12. ASAD
  13. Limitations
  14. CONCLUSIONS

Figures (4)

  • Figure 1: cEEGrid: A C-shaped electrode array is affixed around the ear using a double-sided adhesive. Each cEEGrid consists of 10 electrodes. A. Picture of a cEEGrid placed around the right ear. B. The electrode positions of two cEEGrids for left and right ear.
  • Figure 2: Ear-EEG data from two electrodes positioned on two cEEGrids were selected for TRF analysis. The attended TRFs averaged over the other three unattended TRFs. TRFs of the other three unattended speeches are plotted as colored dashed lines.
  • Figure 3: The result of SR in different decoding window lengths.
  • Figure 4: A. Four different electrode layouts: Gray dot: 59 full electrodes. Red circle: 20 electrodes closest to the cEEGrids. Orange circle: 20 electrodes from central scalp electrodes. Green circle: 20 electrodes from the widespread electrode layout; B. Decoding accuracy for four different electrode layouts