{"id":"https://openalex.org/W4408355619","doi":"https://doi.org/10.1109/icassp49660.2025.10887709","title":"Adapting Single-Channel Pre-trained Transformer Models for Multi-Channel Sound Event Localization and Detection","display_name":"Adapting Single-Channel Pre-trained Transformer Models for Multi-Channel Sound Event Localization and Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355619","doi":"https://doi.org/10.1109/icassp49660.2025.10887709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103203226","display_name":"Changjiang He","orcid":"https://orcid.org/0000-0003-4447-1130"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjiang He","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603499","display_name":"Siyao Cheng","orcid":"https://orcid.org/0000-0002-1263-9907"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyao Cheng","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109676444","display_name":"Jiahua Bao","orcid":"https://orcid.org/0000-0003-0610-4321"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahua Bao","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454005","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6209-6886"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.992900013923645,"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/T11309","display_name":"Music and Audio Processing","score":0.992900013923645,"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":0.9868000149726868,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9772999882698059,"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/computer-science","display_name":"Computer science","score":0.6542691588401794},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5735272765159607},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5540392994880676},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47529137134552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4545414447784424},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3467797636985779},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.22983503341674805},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1983172595500946},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18651852011680603},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10891464352607727},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06786823272705078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542691588401794},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5735272765159607},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5540392994880676},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47529137134552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4545414447784424},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3467797636985779},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.22983503341674805},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1983172595500946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18651852011680603},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10891464352607727},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06786823272705078},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1511170870","https://openalex.org/W2006424233","https://openalex.org/W2103235956","https://openalex.org/W2591013610","https://openalex.org/W2624241755","https://openalex.org/W2810934215","https://openalex.org/W2917254586","https://openalex.org/W2963099423","https://openalex.org/W2964342924","https://openalex.org/W2982429715","https://openalex.org/W2987372735","https://openalex.org/W3107276689","https://openalex.org/W3163193264","https://openalex.org/W3196974791","https://openalex.org/W3206996142","https://openalex.org/W4297841853","https://openalex.org/W4312950730","https://openalex.org/W4324116353","https://openalex.org/W4372263497","https://openalex.org/W4392903703","https://openalex.org/W6628353819","https://openalex.org/W6632323398","https://openalex.org/W6796679619","https://openalex.org/W6797253786","https://openalex.org/W6838853441","https://openalex.org/W6842908365"],"related_works":["https://openalex.org/W1976985527","https://openalex.org/W2043727559","https://openalex.org/W4310420093","https://openalex.org/W2354034738","https://openalex.org/W1963716487","https://openalex.org/W3154635860","https://openalex.org/W4226332880","https://openalex.org/W4298054035","https://openalex.org/W2382303592","https://openalex.org/W1489340745"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,56,75,85,96,109,125,137,155,163,169],"significance":[4],"of":[5],"pre-trained":[6,16],"transformer":[7,17],"audio":[8,18,32,87,113],"models":[9,19,170],"has":[10],"been":[11],"increasingly":[12],"recognized.":[13],"However,":[14],"existing":[15],"are":[20],"based":[21,54],"on":[22,55,157,175],"single-channel":[23,57],"audio.":[24],"They":[25],"cannot":[26],"be":[27],"directly":[28],"applied":[29],"to":[30,73,94,104,107,123,135],"multi-channel":[31,86,112],"for":[33],"Sound":[34],"Event":[35],"Localization":[36],"and":[37,128,152],"Detection":[38],"(SELD)":[39],"tasks.":[40],"To":[41],"address":[42],"this":[43,46],"issue,":[44],"in":[45,78,171],"paper,":[47],"we":[48,64,83,115],"propose":[49,116],"SELD-SSAST,":[50],"a":[51,67,90,117],"novel":[52],"model":[53],"Self-Supervised":[58],"Audio":[59],"Spectrogram":[60],"Transformer":[61],"(SSAST).":[62],"Specifically,":[63],"first":[65],"introduce":[66],"fusion":[68],"feature":[69],"that":[70,145],"enables":[71],"SSAST":[72,92,106],"learn":[74,95,108,136],"unique":[76],"features":[77,88],"SELD":[79],"problems":[80],"effectively.":[81],"Secondly,":[82],"input":[84],"into":[89],"single":[91],"module":[93,122,134],"temporal":[97],"information":[98],"across":[99],"channels":[100],"through":[101],"channel-mixing.":[102],"Finally,":[103],"enable":[105],"relationships":[110],"between":[111,139],"features,":[114],"Convolutional":[118],"Cross":[119],"Attention":[120],"(CCA)":[121],"replace":[124],"Transformer\u2019s":[126],"Self-Attention":[127],"an":[129],"intensity":[130],"vector":[131],"(IV)":[132],"enhanced":[133],"differences":[138],"channel":[140],"features.":[141],"Our":[142],"experiments":[143],"show":[144],"using":[146],"SELD-SSAST":[147,167],"improved":[148],"performance":[149],"by":[150],"23.5%":[151],"20.2%":[153],"over":[154],"baseline":[156],"two":[158,176],"datasets,":[159],"respectively.":[160],"Additionally,":[161],"with":[162],"same":[164],"data":[165],"scale,":[166],"outperforms":[168],"state-of-the-art":[172],"(SOTA)":[173],"methods":[174],"datasets.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}