{"id":"https://openalex.org/W4392903703","doi":"https://doi.org/10.1109/icassp48485.2024.10447181","title":"CST-Former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection","display_name":"CST-Former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903703","doi":"https://doi.org/10.1109/icassp48485.2024.10447181"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447181","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/A5007609195","display_name":"Yusun Shul","orcid":"https://orcid.org/0000-0002-8444-8843"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yusun Shul","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea","School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002212089","display_name":"Jung\u2010Woo Choi","orcid":"https://orcid.org/0000-0002-7264-6017"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Woo Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea","School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007609195"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":7.5724,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.98049815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8686","last_page":"8690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7199587225914001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6661583781242371},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.642797589302063},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5394955277442932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4687417149543762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44920504093170166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43135493993759155},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13323909044265747},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11934587359428406}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7199587225914001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661583781242371},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.642797589302063},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5394955277442932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4687417149543762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44920504093170166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43135493993759155},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13323909044265747},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11934587359428406},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447181","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":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320314062","display_name":"National Research Council","ror":"https://ror.org/02eq2w707"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2810934215","https://openalex.org/W3083274258","https://openalex.org/W3117314925","https://openalex.org/W3126721948","https://openalex.org/W3163193264","https://openalex.org/W3205004157","https://openalex.org/W3206329344","https://openalex.org/W4205689591","https://openalex.org/W4312950730","https://openalex.org/W4321608474","https://openalex.org/W4324116353","https://openalex.org/W4372259962","https://openalex.org/W4372263497","https://openalex.org/W4375868779","https://openalex.org/W4393710905","https://openalex.org/W4393782081","https://openalex.org/W4393895215","https://openalex.org/W6784333009","https://openalex.org/W6838853441","https://openalex.org/W6842908365","https://openalex.org/W6852718469","https://openalex.org/W6862631807","https://openalex.org/W6862861010","https://openalex.org/W6863185053"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Sound":[0],"event":[1],"localization":[2,17],"and":[3,15,31,99,124,134,151],"detection":[4],"(SELD)":[5],"is":[6],"a":[7,65],"task":[8],"for":[9,37,112],"the":[10,16,35,44,53,69,78,132,141,152],"classification":[11],"of":[12,18,20,81,143,154],"sound":[13],"events":[14],"direction":[19],"arrival":[21],"(DoA)":[22],"utilizing":[23],"multichannel":[24],"acoustic":[25],"signals.":[26],"Prior":[27],"studies":[28],"employ":[29],"spectral":[30,54,123],"channel":[32,113],"information":[33],"as":[34],"embedding":[36,109,119],"temporal":[38,100,125],"attention.":[39],"However,":[40],"this":[41,62],"usage":[42],"limits":[43],"deep":[45],"neural":[46],"network":[47],"from":[48,52],"extracting":[49],"meaningful":[50],"features":[51],"or":[55],"spatial":[56],"domains.":[57,86],"Therefore,":[58],"our":[59],"investigation":[60],"in":[61,156],"paper":[63],"presents":[64],"novel":[66],"framework":[67],"termed":[68],"Channel-Spectro-Temporal":[70],"Transformer":[71],"(CST-former)":[72],"that":[73],"bolsters":[74],"SELD":[75,158],"performance":[76],"through":[77,129],"independent":[79],"application":[80],"attention":[82,92,114,145],"mechanisms":[83,93,146],"to":[84,94,116],"distinct":[85,91],"The":[87],"CST-former":[88],"architecture":[89],"employs":[90],"independently":[95],"process":[96],"channel,":[97],"spectral,":[98],"information.":[101,126],"In":[102],"addition,":[103],"we":[104],"propose":[105],"an":[106],"unfolded":[107],"local":[108,122],"(ULE)":[110],"technique":[111],"(CA)":[115],"generate":[117],"informative":[118],"vectors":[120],"including":[121],"Empirical":[127],"validation":[128],"experimentation":[130],"on":[131],"2022":[133],"2023":[135],"DCASE":[136],"Challenge":[137],"task3":[138],"datasets":[139],"affirms":[140],"efficacy":[142],"employing":[144],"separated":[147],"across":[148],"each":[149],"domain":[150],"benefit":[153],"ULE,":[155],"enhancing":[157],"performance.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
