{"id":"https://openalex.org/W4414360487","doi":"https://doi.org/10.24963/ijcai.2025/461","title":"ListenNet: A Lightweight Spatio-Temporal Enhancement Nested Network for Auditory Attention Detection","display_name":"ListenNet: A Lightweight Spatio-Temporal Enhancement Nested Network for Auditory Attention Detection","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360487","doi":"https://doi.org/10.24963/ijcai.2025/461"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/461","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/461","pdf_url":"https://www.ijcai.org/proceedings/2025/0461.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0461.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022709978","display_name":"Xiaoke Yang","orcid":"https://orcid.org/0000-0002-9143-5688"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoke Yang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023999422","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0009-0006-0032-7566"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111322601","display_name":"Ying Chen","orcid":"https://orcid.org/0000-0001-7878-195X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386354","display_name":"Lu Li","orcid":"https://orcid.org/0000-0003-2595-0072"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Li","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687249","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0003-4736-9457"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578581","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0001-9727-366X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":12.9925,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98783985,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4137","last_page":"4145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9567999839782715,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9567999839782715,"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/T11309","display_name":"Music and Audio Processing","score":0.9559000134468079,"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/T10860","display_name":"Speech and Audio Processing","score":0.9501000046730042,"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/robustness","display_name":"Robustness (evolution)","score":0.7121000289916992},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5676000118255615},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5339999794960022},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48840001225471497},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.3776000142097473},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.37619999051094055},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7121000289916992},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41830000281333923},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/461","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/461","pdf_url":"https://www.ijcai.org/proceedings/2025/0461.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/461","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/461","pdf_url":"https://www.ijcai.org/proceedings/2025/0461.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1996838623","display_name":null,"funder_award_id":"62201002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3852078645","display_name":null,"funder_award_id":"STI2030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5007394232","display_name":null,"funder_award_id":"2208085J05","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6912137677","display_name":null,"funder_award_id":"202203a07020008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7616634796","display_name":null,"funder_award_id":"6247077204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8062131859","display_name":null,"funder_award_id":"No.62201002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414360487.pdf","grobid_xml":"https://content.openalex.org/works/W4414360487.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Auditory":[0],"attention":[1,121],"detection":[2],"(AAD)":[3],"aims":[4],"to":[5,101,123],"identify":[6],"the":[7,10,30,87,111,135,151],"direction":[8],"of":[9,33,89,137],"attended":[11],"speaker":[12],"in":[13,142],"multi-speaker":[14],"environments":[15],"from":[16],"brain":[17],"signals,":[18,35],"such":[19],"as":[20],"Electroencephalography":[21],"(EEG)":[22],"signals.":[23],"However,":[24],"existing":[25],"EEG-based":[26],"AAD":[27],"methods":[28,141],"overlook":[29],"spatio-temporal":[31,126],"dependencies":[32,79],"EEG":[34],"limiting":[36],"their":[37],"decoding":[38],"and":[39,72,105,145],"generalization":[40],"abilities.":[41],"To":[42],"address":[43],"these":[44],"issues,":[45],"this":[46],"paper":[47],"proposes":[48],"a":[49],"Lightweight":[50],"Spatio-Temporal":[51],"Enhancement":[52,70],"Nested":[53],"Network":[54],"(ListenNet)":[55],"for":[56],"AAD.":[57],"The":[58,76,93],"ListenNet":[59,138],"has":[60],"three":[61,131],"key":[62],"components:":[63],"Spatio-temporal":[64],"Dependency":[65],"Encoder":[66],"(STDE),":[67],"Multi-scale":[68],"Temporal":[69],"(MSTE),":[71],"Cross-Nested":[73],"Attention":[74],"(CNA).":[75],"STDE":[77],"reconstructs":[78],"between":[80],"consecutive":[81],"time":[82],"windows":[83],"across":[84],"channels,":[85],"improving":[86],"robustness":[88],"dynamic":[90,120],"pattern":[91],"extraction.":[92],"MSTE":[94],"captures":[95],"temporal":[96,107],"features":[97,115],"at":[98],"multiple":[99],"scales":[100],"represent":[102],"both":[103,143],"fine-grained":[104],"long-range":[106],"patterns.":[108],"In":[109],"addition,":[110],"CNA":[112],"integrates":[113],"hierarchical":[114],"more":[116],"effectively":[117],"through":[118],"novel":[119],"mechanisms":[122],"capture":[124],"deep":[125],"correlations.":[127],"Experimental":[128],"results":[129],"on":[130],"public":[132],"datasets":[133],"demonstrate":[134],"superiority":[136],"over":[139],"state-of-the-art":[140],"subject-dependent":[144],"challenging":[146],"subject-independent":[147],"settings,":[148],"while":[149],"reducing":[150],"trainable":[152],"parameter":[153],"count":[154],"by":[155],"approximately":[156],"7":[157],"times.":[158],"Code":[159],"is":[160],"available":[161],"at:https://github.com/fchest/ListenNet.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}