Yixiang Niu, Ning Chen, Hongqing Zhu, Guangqiang Li, Yibo Chen
{"title":"基于大脑拓扑建模和特征分布配准的受试者无关听觉空间注意力检测","authors":"Yixiang Niu, Ning Chen, Hongqing Zhu, Guangqiang Li, Yibo Chen","doi":"10.1016/j.heares.2024.109104","DOIUrl":null,"url":null,"abstract":"<div><p>Auditory spatial attention detection (ASAD) seeks to determine which speaker in a surround sound field a listener is focusing on based on the one’s brain biosignals. Although existing studies have achieved ASAD from a single-trial electroencephalogram (EEG), the huge inter-subject variability makes them generally perform poorly in cross-subject scenarios. Besides, most ASAD methods do not take full advantage of topological relationships between EEG channels, which are crucial for high-quality ASAD. Recently, some advanced studies have introduced graph-based brain topology modeling into ASAD, but how to calculate edge weights in a graph to better capture actual brain connectivity is worthy of further investigation. To address these issues, we propose a new ASAD method in this paper. First, we model a multi-channel EEG segment as a graph, where differential entropy serves as the node feature, and a static adjacency matrix is generated based on inter-channel mutual information to quantify brain functional connectivity. Then, different subjects’ EEG graphs are encoded into a shared embedding space through a total variation graph neural network. Meanwhile, feature distribution alignment based on multi-kernel maximum mean discrepancy is adopted to learn subject-invariant patterns. Note that we align EEG embeddings of different subjects to reference distributions rather than align them to each other for the purpose of privacy preservation. A series of experiments on open datasets demonstrate that the proposed model outperforms state-of-the-art ASAD models in cross-subject scenarios with relatively low computational complexity, and feature distribution alignment improves the generalizability of the proposed model to a new subject.</p></div>","PeriodicalId":12881,"journal":{"name":"Hearing Research","volume":"453 ","pages":"Article 109104"},"PeriodicalIF":2.5000,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Subject-independent auditory spatial attention detection based on brain topology modeling and feature distribution alignment\",\"authors\":\"Yixiang Niu, Ning Chen, Hongqing Zhu, Guangqiang Li, Yibo Chen\",\"doi\":\"10.1016/j.heares.2024.109104\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Auditory spatial attention detection (ASAD) seeks to determine which speaker in a surround sound field a listener is focusing on based on the one’s brain biosignals. Although existing studies have achieved ASAD from a single-trial electroencephalogram (EEG), the huge inter-subject variability makes them generally perform poorly in cross-subject scenarios. Besides, most ASAD methods do not take full advantage of topological relationships between EEG channels, which are crucial for high-quality ASAD. Recently, some advanced studies have introduced graph-based brain topology modeling into ASAD, but how to calculate edge weights in a graph to better capture actual brain connectivity is worthy of further investigation. To address these issues, we propose a new ASAD method in this paper. First, we model a multi-channel EEG segment as a graph, where differential entropy serves as the node feature, and a static adjacency matrix is generated based on inter-channel mutual information to quantify brain functional connectivity. Then, different subjects’ EEG graphs are encoded into a shared embedding space through a total variation graph neural network. Meanwhile, feature distribution alignment based on multi-kernel maximum mean discrepancy is adopted to learn subject-invariant patterns. Note that we align EEG embeddings of different subjects to reference distributions rather than align them to each other for the purpose of privacy preservation. A series of experiments on open datasets demonstrate that the proposed model outperforms state-of-the-art ASAD models in cross-subject scenarios with relatively low computational complexity, and feature distribution alignment improves the generalizability of the proposed model to a new subject.</p></div>\",\"PeriodicalId\":12881,\"journal\":{\"name\":\"Hearing Research\",\"volume\":\"453 \",\"pages\":\"Article 109104\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2024-08-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Hearing Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0378595524001576\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUDIOLOGY & SPEECH-LANGUAGE PATHOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hearing Research","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378595524001576","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUDIOLOGY & SPEECH-LANGUAGE PATHOLOGY","Score":null,"Total":0}
Subject-independent auditory spatial attention detection based on brain topology modeling and feature distribution alignment
Auditory spatial attention detection (ASAD) seeks to determine which speaker in a surround sound field a listener is focusing on based on the one’s brain biosignals. Although existing studies have achieved ASAD from a single-trial electroencephalogram (EEG), the huge inter-subject variability makes them generally perform poorly in cross-subject scenarios. Besides, most ASAD methods do not take full advantage of topological relationships between EEG channels, which are crucial for high-quality ASAD. Recently, some advanced studies have introduced graph-based brain topology modeling into ASAD, but how to calculate edge weights in a graph to better capture actual brain connectivity is worthy of further investigation. To address these issues, we propose a new ASAD method in this paper. First, we model a multi-channel EEG segment as a graph, where differential entropy serves as the node feature, and a static adjacency matrix is generated based on inter-channel mutual information to quantify brain functional connectivity. Then, different subjects’ EEG graphs are encoded into a shared embedding space through a total variation graph neural network. Meanwhile, feature distribution alignment based on multi-kernel maximum mean discrepancy is adopted to learn subject-invariant patterns. Note that we align EEG embeddings of different subjects to reference distributions rather than align them to each other for the purpose of privacy preservation. A series of experiments on open datasets demonstrate that the proposed model outperforms state-of-the-art ASAD models in cross-subject scenarios with relatively low computational complexity, and feature distribution alignment improves the generalizability of the proposed model to a new subject.
期刊介绍:
The aim of the journal is to provide a forum for papers concerned with basic peripheral and central auditory mechanisms. Emphasis is on experimental and clinical studies, but theoretical and methodological papers will also be considered. The journal publishes original research papers, review and mini- review articles, rapid communications, method/protocol and perspective articles.
Papers submitted should deal with auditory anatomy, physiology, psychophysics, imaging, modeling and behavioural studies in animals and humans, as well as hearing aids and cochlear implants. Papers dealing with the vestibular system are also considered for publication. Papers on comparative aspects of hearing and on effects of drugs and environmental contaminants on hearing function will also be considered. Clinical papers will be accepted when they contribute to the understanding of normal and pathological hearing functions.