{"id":"https://openalex.org/W4392910326","doi":"https://doi.org/10.1109/icassp48485.2024.10448271","title":"Investigating Self-Supervised Deep Representations for EEG-Based Auditory Attention Decoding","display_name":"Investigating Self-Supervised Deep Representations for EEG-Based Auditory Attention Decoding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910326","doi":"https://doi.org/10.1109/icassp48485.2024.10448271"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448271","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5078637653","display_name":"Karan Thakkar","orcid":"https://orcid.org/0000-0002-6803-1116"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karan Thakkar","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Audio Perception,USA","Laboratory for Computational Audio Perception, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Audio Perception,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Audio Perception, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Audio Perception,USA","Laboratory for Computational Audio Perception, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Audio Perception,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Audio Perception, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Audio Perception,USA","Laboratory for Computational Audio Perception, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Audio Perception,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Audio Perception, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078637653"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"],"apc_list":null,"apc_paid":null,"fwci":1.3169,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78537361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1241","last_page":"1245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994999766349792,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7590165138244629},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7468150854110718},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.7012792825698853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6626983880996704},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.578349769115448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5628413558006287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5251581072807312},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43163636326789856},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40027493238449097},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18544679880142212},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14557477831840515},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.09518119692802429}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7590165138244629},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7468150854110718},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.7012792825698853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6626983880996704},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.578349769115448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5628413558006287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251581072807312},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43163636326789856},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40027493238449097},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18544679880142212},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14557477831840515},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.09518119692802429},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448271","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1621710783","https://openalex.org/W2158904676","https://openalex.org/W2169918686","https://openalex.org/W2191779130","https://openalex.org/W2283417180","https://openalex.org/W2408166852","https://openalex.org/W2558802391","https://openalex.org/W2606067354","https://openalex.org/W2953132115","https://openalex.org/W2982223350","https://openalex.org/W2996428491","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3185053423","https://openalex.org/W3191474079","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209938276","https://openalex.org/W3209984917","https://openalex.org/W4316468787","https://openalex.org/W4389542986","https://openalex.org/W4393768900","https://openalex.org/W4393883034","https://openalex.org/W6780218876","https://openalex.org/W6803274909","https://openalex.org/W6863094196"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450","https://openalex.org/W55249799"],"abstract_inverted_index":{"Auditory":[0],"Attention":[1],"Decoding":[2],"(AAD)":[3],"algorithms":[4],"play":[5],"a":[6,50,58],"crucial":[7],"role":[8],"in":[9,28,119],"isolating":[10],"desired":[11],"sound":[12],"sources":[13],"within":[14],"challenging":[15],"acoustic":[16],"environments":[17],"directly":[18],"from":[19,78],"brain":[20,121],"activity.":[21],"Although":[22],"recent":[23],"research":[24],"has":[25,40],"shown":[26],"promise":[27],"AAD":[29,98,144,154],"using":[30,125],"shallow":[31,72],"representations":[32,48,139],"such":[33],"as":[34],"auditory":[35],"envelope":[36],"and":[37,70,84,107,140],"spectrogram,":[38],"there":[39],"been":[41],"limited":[42],"exploration":[43],"of":[44,64,94,104,116,134,137,159],"deep":[45,69,95,126,160],"Self-Supervised":[46],"(SS)":[47],"on":[49,143],"larger":[51],"scale.":[52],"In":[53],"this":[54],"study,":[55],"we":[56,130],"undertake":[57],"comprehensive":[59],"investigation":[60],"into":[61],"the":[62,92,105,120,132,149,157],"performance":[63],"linear":[65],"decoders":[66],"across":[67],"12":[68],"2":[71],"representations,":[73],"applied":[74],"to":[75],"EEG":[76],"data":[77],"multiple":[79,85],"studies":[80],"spanning":[81],"57":[82],"subjects":[83],"languages.":[86],"Our":[87],"experimental":[88],"results":[89],"consistently":[90],"reveal":[91],"superiority":[93],"features":[96],"for":[97,151],"at":[99],"decoding":[100],"background":[101],"speakers,":[102],"regardless":[103],"datasets":[106],"analysis":[108],"windows.":[109],"This":[110],"result":[111],"indicates":[112],"possible":[113],"nonlinear":[114,127],"encoding":[115],"unattended":[117],"signals":[118],"that":[122],"are":[123],"revealed":[124],"features.":[128],"Additionally,":[129],"analyze":[131],"impact":[133],"different":[135],"layers":[136],"SS":[138],"window":[141],"sizes":[142],"performance.":[145],"These":[146],"findings":[147],"underscore":[148],"potential":[150],"enhancing":[152],"EEG-based":[153],"systems":[155],"through":[156],"integration":[158],"feature":[161],"representations.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}