{"id":"https://openalex.org/W4406461491","doi":"https://doi.org/10.1109/slt61566.2024.10832311","title":"SWIM: Short-Window CNN Integrated With Mamba for EEG-Based Auditory Spatial Attention Decoding","display_name":"SWIM: Short-Window CNN Integrated With Mamba for EEG-Based Auditory Spatial Attention Decoding","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461491","doi":"https://doi.org/10.1109/slt61566.2024.10832311"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100357828","display_name":"Ziyang Zhang","orcid":"https://orcid.org/0000-0001-5942-0235"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyang Zhang","raw_affiliation_strings":["Tsinghua University,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078469559","display_name":"Andrew Thwaites","orcid":"https://orcid.org/0000-0002-6237-7140"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Thwaites","raw_affiliation_strings":["University College London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University College London,United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062680873","display_name":"Alexandra Woolgar","orcid":"https://orcid.org/0000-0002-8453-7424"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandra Woolgar","raw_affiliation_strings":["University of Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073346961","display_name":"Brian C. J. Moore","orcid":"https://orcid.org/0000-0001-7071-0671"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Brian Moore","raw_affiliation_strings":["University of Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100357828"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27193958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1031","last_page":"1038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7494315505027771},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.69352787733078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6656054258346558},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.6609673500061035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6124330163002014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.329546183347702},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19785842299461365},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.15590685606002808},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10394352674484253}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7494315505027771},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.69352787733078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656054258346558},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.6609673500061035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6124330163002014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.329546183347702},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19785842299461365},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.15590685606002808},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10394352674484253},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1991139021","https://openalex.org/W2064675550","https://openalex.org/W2116341502","https://openalex.org/W2158904676","https://openalex.org/W2238628508","https://openalex.org/W2408166852","https://openalex.org/W2549392078","https://openalex.org/W2590420622","https://openalex.org/W2755231251","https://openalex.org/W2771075519","https://openalex.org/W2889782437","https://openalex.org/W2913201307","https://openalex.org/W2936774411","https://openalex.org/W2940955708","https://openalex.org/W2973049979","https://openalex.org/W2991185935","https://openalex.org/W3046474724","https://openalex.org/W3093647835","https://openalex.org/W3095623684","https://openalex.org/W3126966983","https://openalex.org/W3159696612","https://openalex.org/W3160453855","https://openalex.org/W4206654584","https://openalex.org/W4206798246","https://openalex.org/W4221074078","https://openalex.org/W4301367357","https://openalex.org/W4308834535","https://openalex.org/W4375868845","https://openalex.org/W4377089539","https://openalex.org/W4383960611","https://openalex.org/W4385245566","https://openalex.org/W4385863621","https://openalex.org/W4388899519","https://openalex.org/W4389326242","https://openalex.org/W4391160633","https://openalex.org/W4392903877","https://openalex.org/W4396818493","https://openalex.org/W4399253084","https://openalex.org/W6631190155","https://openalex.org/W6723019446","https://openalex.org/W6736429057","https://openalex.org/W6789805323","https://openalex.org/W6803444062","https://openalex.org/W6810325043","https://openalex.org/W6855510309","https://openalex.org/W6858131838","https://openalex.org/W6859298233","https://openalex.org/W6866460473","https://openalex.org/W6868106102","https://openalex.org/W6868789466"],"related_works":["https://openalex.org/W2390901981","https://openalex.org/W2922348724","https://openalex.org/W200322357","https://openalex.org/W2130428257","https://openalex.org/W2109115373","https://openalex.org/W4308951944","https://openalex.org/W2057366091","https://openalex.org/W4312960290","https://openalex.org/W2049513647","https://openalex.org/W2988848585"],"abstract_inverted_index":{"In":[0,21],"complex":[1],"auditory":[2,6,45,126],"environments,":[3],"the":[4,9,42,87,91,101,132,146,164,173],"human":[5],"system":[7],"possesses":[8],"remarkable":[10],"ability":[11],"to":[12,100,125,130,172],"focus":[13],"on":[14,56,90],"a":[15,24,29,67,74,81,120,168],"specific":[16],"speaker":[17],"while":[18],"disregarding":[19],"others.":[20],"this":[22],"study,":[23],"new":[25],"model":[26,113,122],"named":[27],"SWIM,":[28],"short-window":[30,68],"convolution":[31],"neural":[32],"network":[33],"(CNN)":[34],"integrated":[35],"with":[36],"Mamba,":[37,118,145],"is":[38,66,98,119,180],"proposed":[39,147],"for":[40],"identifying":[41],"locus":[43],"of":[44,61,84,103,160],"attention":[46,128],"(left":[47],"or":[48],"right)":[49],"from":[50,135],"electroencephalography":[51],"(EEG)":[52],"signals":[53],"without":[54],"relying":[55],"speech":[57],"envelopes.":[58],"SWIM":[59,148],"consists":[60],"two":[62],"parts.":[63],"The":[64,115,177],"first":[65,123],"CNN":[69,106],"($\\mathrm{SW}_{\\mathrm{CNN}}$),":[70],"which":[71,162],"acts":[72],"as":[73],"short-term":[75,152],"EEG":[76],"feature":[77],"extractor":[78],"and":[79,112,144,153,156],"achieves":[80,157],"final":[82],"accuracy":[83,159],"84.9%":[85],"in":[86],"leave-one-speaker-out":[88],"setup":[89],"widely":[92],"used":[93],"KUL":[94],"dataset.":[95],"This":[96],"improvement":[97],"due":[99],"use":[102],"an":[104,158],"improved":[105],"structure,":[107],"data":[108],"augmentation,":[109],"multitask":[110],"training,":[111],"combination.":[114],"second":[116],"part,":[117],"sequence":[121],"applied":[124],"spatial":[127],"decoding":[129],"leverage":[131],"long-term":[133,154],"dependency":[134],"previous":[136,174],"$\\mathrm{SW}_{\\mathrm{CNN}}$":[137,143],"time":[138],"steps.":[139],"By":[140],"joint":[141],"training":[142],"structure":[149],"uses":[150],"both":[151],"information":[155],"86.2%,":[161],"reduces":[163],"classification":[165],"errors":[166],"by":[167],"relative":[169],"31.0%":[170],"compared":[171],"state-of-the-art":[175],"result.":[176],"source":[178],"code":[179],"available":[181],"at":[182],"https://github.com/windowso/SWIM-ASAD.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
