cs.SD - 2023-11-01

Investigating Self-Supervised Deep Representations for EEG-based Auditory Attention Decoding

  • paper_url: http://arxiv.org/abs/2311.00814
  • repo_url: None
  • paper_authors: Karan Thakkar, Jiarui Hai, Mounya Elhilali
  • for: 这篇研究旨在探索深度自愿学习(SS)表现在脑活动讯号处理中的可行性,尤其是在复杂的声音环境中对需要的声音源进行隔离。
  • methods: 本研究使用了12个深度和2个浅层表现,对EEG数据自57名参与者和多种语言进行了评估。
  • results: 实验结果显示,深度特征在背景声音源隔离中表现出超过浅层特征,无论是哪些数据和分析窗口。这显示可能存在脑中隐藏的非线性编码,深度非线性特征可能会更好地捕捉这些隐藏的讯号。此外,研究还分析了不同层次的SS表现和窗口大小对AAD性能的影响。
    Abstract Auditory Attention Decoding (AAD) algorithms play a crucial role in isolating desired sound sources within challenging acoustic environments directly from brain activity. Although recent research has shown promise in AAD using shallow representations such as auditory envelope and spectrogram, there has been limited exploration of deep Self-Supervised (SS) representations on a larger scale. In this study, we undertake a comprehensive investigation into the performance of linear decoders across 12 deep and 2 shallow representations, applied to EEG data from multiple studies spanning 57 subjects and multiple languages. Our experimental results consistently reveal the superiority of deep features for AAD at decoding background speakers, regardless of the datasets and analysis windows. This result indicates possible nonlinear encoding of unattended signals in the brain that are revealed using deep nonlinear features. Additionally, we analyze the impact of different layers of SS representations and window sizes on AAD performance. These findings underscore the potential for enhancing EEG-based AAD systems through the integration of deep feature representations.
    摘要 听觉注意力解码(AAD)算法在复杂的听觉环境中直接从大脑活动中隔离感兴趣的声音源。although recent research has shown promise in AAD using shallow representations such as auditory envelope and spectrogram, there has been limited exploration of deep Self-Supervised (SS) representations on a larger scale. In this study, we undertake a comprehensive investigation into the performance of linear decoders across 12 deep and 2 shallow representations, applied to EEG data from multiple studies spanning 57 subjects and multiple languages. Our experimental results consistently reveal the superiority of deep features for AAD at decoding background speakers, regardless of the datasets and analysis windows. This result indicates possible nonlinear encoding of unattended signals in the brain that are revealed using deep nonlinear features. Additionally, we analyze the impact of different layers of SS representations and window sizes on AAD performance. These findings underscore the potential for enhancing EEG-based AAD systems through the integration of deep feature representations.Here's the word-for-word translation:听觉注意力解码算法在复杂的听觉环境中直接从大脑活动中隔离感兴趣的声音源。although recent research has shown promise in AAD using shallow representations such as auditory envelope and spectrogram, there has been limited exploration of deep Self-Supervised (SS) representations on a larger scale. In this study, we undertake a comprehensive investigation into the performance of linear decoders across 12 deep and 2 shallow representations, applied to EEG data from multiple studies spanning 57 subjects and multiple languages. Our experimental results consistently reveal the superiority of deep features for AAD at decoding background speakers, regardless of the datasets and analysis windows. This result indicates possible nonlinear encoding of unattended signals in the brain that are revealed using deep nonlinear features. Additionally, we analyze the impact of different layers of SS representations and window sizes on AAD performance. These findings underscore the potential for enhancing EEG-based AAD systems through the integration of deep feature representations.

C2C: Cough to COVID-19 Detection in BHI 2023 Data Challenge

  • paper_url: http://arxiv.org/abs/2311.00364
  • repo_url: None
  • paper_authors: Woo-Jin Chung, Miseul Kim, Hong-Goo Kang
  • For: The paper is written for the BHI 2023 Data Competition: Sensor challenge, with the goal of developing an acoustic-based COVID-19 diagnosis system.* Methods: The paper uses pre-processing of input signals, cough-related representation extraction leveraging Wav2vec2.0, and data augmentation to develop the Cough to COVID-19 (C2C) system.* Results: The paper demonstrates the promising potential of C2C to enhance the diagnostic accuracy of COVID-19 via cough signals, with a ROC-AUC value of 0.7810 in the context of COVID-19 diagnosis.Here is the text in Simplified Chinese:* 为:本文为BHI 2023数据比赛:感测挑战提交作品,旨在开发基于听音的 COVID-19诊断系统。* 方法:本文使用输入信号预处理、基于 Wav2vec2.0 的喊喊相关表示EXTRACT、数据增强等方法开发 Cough to COVID-19 (C2C) 系统。* 结果:本文通过实验发现,C2C 系统可以在 COVID-19 诊断中提高诊断精度,ROC-AUC 值达0.7810。
    Abstract This report describes our submission to BHI 2023 Data Competition: Sensor challenge. Our Audio Alchemists team designed an acoustic-based COVID-19 diagnosis system, Cough to COVID-19 (C2C), and won the 1st place in the challenge. C2C involves three key contributions: pre-processing of input signals, cough-related representation extraction leveraging Wav2vec2.0, and data augmentation. Through experimental findings, we demonstrate C2C's promising potential to enhance the diagnostic accuracy of COVID-19 via cough signals. Our proposed model achieves a ROC-AUC value of 0.7810 in the context of COVID-19 diagnosis. The implementation details and the python code can be found in the following link: https://github.com/Woo-jin-Chung/BHI_2023_challenge_Audio_Alchemists
    摘要 这份报告描述了我们对BHI 2023数据比赛:感知挑战的提交。我们的Audio Alchemists团队设计了基于声音的COVID-19诊断系统,叫做Cough to COVID-19(C2C),并在挑战中获得了第一名。C2C包括三个关键贡献:输入信号的预处理、基于Wav2vec2.0的喊喊相关特征提取,以及数据扩展。通过实验发现,我们示出了C2C在COVID-19诊断中的潜在优势,可以提高COVID-19诊断的准确率。我们的提出的模型在COVID-19诊断上 achievement ROC-AUC值为0.7810。更多细节和python代码可以在以下链接中找到:https://github.com/Woo-jin-Chung/BHI_2023_challenge_Audio_Alchemists。