Low-Latency Auditory Spatial Attention Detection Based on Spectro-Spatial Features from EEG

Cai, Siqi; Sun, Pengcheng; Schultz, Tanja; Li, Haizhou

doi:10.1109/embc46164.2021.9630902

Cited by 15 publications

(41 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed NI-AAD model shows a relatively high decoding performance with an accuracy of 82.8% (SD: 7.49) for 1s, 87.1% (SD: 6.17) for 2 s, and 91.2% (SD: 5.13) for 5s decision window. Consistent with previous studies [6], [30], [31], the AAD accuracy generally decreases for shorter decision window lengths. However, we are encouraged by the relatively high AAD result on the 0.1 s decision window 73.1% (SD: 7.26), which could potentially be suitable for real-time neuro-steered hearing aids.…”

Section: A Attention Decoding Accuracysupporting

confidence: 90%

“…Performance during this grid search was measured on the validation set. Consistent with previous studies [30], [31], the AAD accuracy is defined as the percentage of correctly classified decision windows on the test set.…”

Section: Model Implementationmentioning

confidence: 87%

“…As shown in Fig. 1, we employed the SSF representation method to extract the topographic specificity of alpha power from original EEG data [31].…”

Section: A Spatio-spectral Feature Representationmentioning

confidence: 99%

“…Moreover, it is a longstanding problem in computational neuroscience to understand how the plasticity dynamics are organized in multilayer (deep) biological neural networks to achieve efficient data-driven learning [42]. In general, the success of previous CNN models for EEG-based AAD tasks [30], [31] gives rise to questioning whether the factors to their success are compatible with their biological ingredients, viz., SNNs.…”

Section: Spiking Neural Network Classifiermentioning

confidence: 99%

“…Unfortunately, this approach does not benefit from feature representation as they directly take the C × T -dimensional matrix, where C and T , respectively, denote the total number of EEG channels and time duration, as the input. Considering that the topographic specificity of alpha power (8)(9)(10)(11)(12)(13) indicates the direction of auditory attention to speech [24], [25], [27], [28], we developed a novel spatio-spectral feature (SSF) representation method that retains task-related information in a pilot study [31] and outperforms the up-to-date models in AAD tasks [20], [30], [32].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Neural-Inspired Architecture for EEG-Based Auditory Attention Detection

Cai

et al. 2022

IEEE Trans. Human-Mach. Syst.

Self Cite

View full text Add to dashboard Cite

Humans have the ability to focus on one of the sound sources in a noisy scene, which is critical for everyday communication. Auditory attention detection (AAD) seeks to detect selective attention from one's brain signals. For AAD to be useful in braincomputer interface applications, new approaches with low computational cost, high classification performance, and low latency are required to be developed. In this study, we proposed a novel neuralinspired architecture to mimic the neural computation and coding strategy in the brain for electroencephalography-based AAD. We validated our model through data visualization, and conducted experiments on two publicly available databases. For both KUL and DTU databases, it outperforms both linear and convolutional neural network (CNN) models with consistent improvements from 1 s to 5 s decision windows in terms of detection accuracy. Although the accuracy of the proposed neural-inspired model is inferior to the state-of-the-art spatio-spectral feature (SSF)-CNN model, the computational cost of our model is less than 1% of SSF-CNN's. Moreover, the neural-inspired decoder is more hardware friendly and energy-efficient due to its biological computing scheme. Overall, the proposed neural-inspired architecture realizes a fast, accurate, and low energy expenditure AAD, which is a big step forward towards practical neuro-steered hearing aids.

show abstract

Section: A Attention Decoding Accuracysupporting

confidence: 90%

Section: Model Implementationmentioning

confidence: 87%

“…As shown in Fig. 1, we employed the SSF representation method to extract the topographic specificity of alpha power from original EEG data [31].…”

Section: A Spatio-spectral Feature Representationmentioning

confidence: 99%

Section: Spiking Neural Network Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Neural-Inspired Architecture for EEG-Based Auditory Attention Detection

Cai

et al. 2022

IEEE Trans. Human-Mach. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

Brain connectivity and time-frequency fusion-based auditory spatial attention detection

Niu,

Chen,

Zhu

et al. 2024

Neuroscience

View full text Add to dashboard Cite

Detecting the locus of auditory attention based on the spectro-spatial-temporal analysis of EEG

Jiang

Chen²,

Jin³

2022

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Auditory Attention Decoding (AAD) determines which speaker the listener is focusing on by analyzing his/her EEG. CNN was adopted to extract Spectro-Spatial-Feature (SSF) from short-time-interval of EEG to detect auditory spatial attention without stimuli. However, the following factors are not considered in SSF-CNN scheme. i) Single-band frequency analysis cannot represent the EEG pattern precisely. ii) The power cannot represent the EEG feature related to the dynamic patterns of the attended auditory stimulus. iii) The temporal feature of EEG representing the relationship between EEG and attended stimulus is not extracted. To solve these problems, SSF-CNN scheme was modified. Approach. i) Multiple-frequency bands, but not a single alpha frequency band, of EEG, were analyzed to represent the EEG pattern more precisely. ii) Differential Entropy (DE), but not power, was extracted from each frequency band to represent the disorder degree of EEG, which was related to the dynamic patterns of the attended auditory stimulus. iii) CNN and Convolutional-Long-Short-Term-Memory (ConvLSTM) were combined to extract spectro-spatial-temporal features from the 3-D descriptor sequence constructed based on the topographical activity maps of multiple-frequency bands. Main results. Experimental results on KUL, DTU, and PKU with 0.1s, 1s, 2s, and 5s decision windows demonstrated that: i) The proposed model outperformed SSF-CNN and state-of-the-art AAD models. Specifically, when the auditory stimulus was unavailable, AAD accuracy could be enhanced by at least 3:25%, 3:96%, and 5:08% on KUL, DTU, and PKU, respectively, compared with the baselines. And, on KUL, the longer decision window corresponded to lower enhancement, while on both DTU and PKU, the longer decision window corresponded to higher enhancement, except for two cases when decision window length was 2s on PKU or 5s on DTU. ii) Each modification contributed to the performance enhancement. Significance. DE feature, multi-band frequency analysis, and ConvLSTM-based temporal analysis help to enhance AAD accuracy.

show abstract

Low-Latency Auditory Spatial Attention Detection Based on Spectro-Spatial Features from EEG

Cited by 15 publications

References 21 publications

A Neural-Inspired Architecture for EEG-Based Auditory Attention Detection

A Neural-Inspired Architecture for EEG-Based Auditory Attention Detection

Brain connectivity and time-frequency fusion-based auditory spatial attention detection

Detecting the locus of auditory attention based on the spectro-spatial-temporal analysis of EEG

Contact Info

Product

Resources

About