Scholarlink

<p>Purpose: In the context of a multi-speaker “cocktail party” scenario where listeners selectively focus on specific speakers, human auditory attention networks have shown a strong correlation with Electroencephalography (EEG) measurements. However, current EEG-based auditory attention detection (AAD) methods, mostly using artificial neural networks (ANN), face limitations on edge computing platforms due to extended decision windows, high power consumption, and substantial memory requirements linked to multiple EEG channels. Methods: This paper introduces a novel hybrid convolutional-spiking neural network (CNN-SNN) architecture, inspired by the auditory cortex, combining EEG data with multi-speaker speech envelopes, enabling effective auditory attention decoding within 0.5-s timeframes. Our approach reduces EEG channels, minimizes computational operations, and quantizes weight parameters while maintaining high accuracy. Results: We validate this approach on our dataset and compare it to state-of-the-art methods on a publicly available dataset. CNN-SNN demonstrates superior performance, achieving up to 10% increase in decoding accuracy, while using 87.5% fewer EEG channels and 75% smaller bit precision for weight quantization compared to existing methods. Conclusion: These results offer promise for edge computing applications, such as hearing aids, emphasizing short decision windows, minimal EEG channels, and strict power and memory constraints.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Corticomorphic Hybrid CNN-SNN Architecture for EEG-Based Low-Footprint Low-Latency Auditory Attention Detection

  • 期刊论文

  • 发表日期：

    2026年3月17日

查看全文
  • Richard Gall,
  • Deniz Kocanaogullari,
  • Murat Akcakaya,
  • Nicole Laffan,
  • Deniz Erdogmus,
  • Rajkumar Kubendran

摘要

Purpose: In the context of a multi-speaker “cocktail party” scenario where listeners selectively focus on specific speakers, human auditory attention networks have shown a strong correlation with Electroencephalography (EEG) measurements. However, current EEG-based auditory attention detection (AAD) methods, mostly using artificial neural networks (ANN), face limitations on edge computing platforms due to extended decision windows, high power consumption, and substantial memory requirements linked to multiple EEG channels. Methods: This paper introduces a novel hybrid convolutional-spiking neural network (CNN-SNN) architecture, inspired by the auditory cortex, combining EEG data with multi-speaker speech envelopes, enabling effective auditory attention decoding within 0.5-s timeframes. Our approach reduces EEG channels, minimizes computational operations, and quantizes weight parameters while maintaining high accuracy. Results: We validate this approach on our dataset and compare it to state-of-the-art methods on a publicly available dataset. CNN-SNN demonstrates superior performance, achieving up to 10% increase in decoding accuracy, while using 87.5% fewer EEG channels and 75% smaller bit precision for weight quantization compared to existing methods. Conclusion: These results offer promise for edge computing applications, such as hearing aids, emphasizing short decision windows, minimal EEG channels, and strict power and memory constraints.