{"id":"https://openalex.org/W4382787045","doi":"https://doi.org/10.1186/s13636-023-00292-9","title":"Dual-branch attention module-based network with parameter sharing for joint sound event detection and localization","display_name":"Dual-branch attention module-based network with parameter sharing for joint sound event detection and localization","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4382787045","doi":"https://doi.org/10.1186/s13636-023-00292-9"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00292-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00292-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00292-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00292-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101564492","display_name":"Yuting Zhou","orcid":"https://orcid.org/0000-0003-2254-2815"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Zhou","raw_affiliation_strings":["Information Engineering Dept, Beijing University of Chemical Technology, No.15 North Third Ring Road East, Beijing, 100029, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering Dept, Beijing University of Chemical Technology, No.15 North Third Ring Road East, Beijing, 100029, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046771940","display_name":"Hongjie Wan","orcid":"https://orcid.org/0000-0002-4982-0689"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongjie Wan","raw_affiliation_strings":["Information Engineering Dept, Beijing University of Chemical Technology, No.15 North Third Ring Road East, Beijing, 100029, China"],"raw_orcid":"https://orcid.org/0000-0002-4982-0689","affiliations":[{"raw_affiliation_string":"Information Engineering Dept, Beijing University of Chemical Technology, No.15 North Third Ring Road East, Beijing, 100029, China","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046771940"],"corresponding_institution_ids":["https://openalex.org/I75390827"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.8019,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69184402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2023","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7643634676933289},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5486370921134949},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5110772848129272},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4747008681297302},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.45213714241981506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4409020245075226},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4336821138858795},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4295116364955902},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4285355806350708},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4234831929206848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4166172444820404},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2605794072151184},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13186240196228027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643634676933289},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5486370921134949},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5110772848129272},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4747008681297302},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.45213714241981506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4409020245075226},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4336821138858795},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4295116364955902},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4285355806350708},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4234831929206848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4166172444820404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2605794072151184},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13186240196228027},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-023-00292-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00292-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00292-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d61bc4c192794481983ba08b224b34df","is_oa":true,"landing_page_url":"https://doaj.org/article/d61bc4c192794481983ba08b224b34df","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-15 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00292-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00292-9","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00292-9","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382787045.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1972567154","https://openalex.org/W2103235956","https://openalex.org/W2123843894","https://openalex.org/W2132920253","https://openalex.org/W2188041026","https://openalex.org/W2292996718","https://openalex.org/W2942551338","https://openalex.org/W2963677766","https://openalex.org/W3005741390","https://openalex.org/W3097777922","https://openalex.org/W3098454764","https://openalex.org/W4221154745","https://openalex.org/W6611786062","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W2379948177","https://openalex.org/W2107949441"],"abstract_inverted_index":{"Abstract":[0],"The":[1,95,157],"goal":[2],"of":[3,25,35,41,69,75,107,127,206],"sound":[4,15,164],"event":[5,16],"detection":[6],"and":[7,18,44,65,109,116,124,155,211],"localization":[8,129],"(SELD)":[9],"is":[10,47,97],"to":[11,80,138],"identify":[12],"each":[13],"individual":[14],"class":[17],"its":[19,29],"activity":[20],"time":[21,34,172],"from":[22],"a":[23,66,85],"piece":[24],"audio,":[26],"while":[27],"estimating":[28],"spatial":[30],"location":[31],"at":[32],"the":[33,39,72,90,101,128,139,147,151,170,177,186,194,204,207],"activity.":[36],"Conformer":[37],"combines":[38],"advantages":[40],"convolutional":[42],"layers":[43],"Transformer,":[45],"which":[46,111,143],"effective":[48],"in":[49,169],"tasks":[50],"such":[51],"as":[52],"speech":[53],"recognition.":[54],"However,":[55],"it":[56],"achieves":[57,189],"high":[58],"performance":[59,192],"relying":[60],"on":[61,100],"complex":[62],"network":[63,87],"structure":[64],"large":[67],"number":[68],"computations.":[70],"In":[71,131],"SELD":[73,141,191],"task":[74,182],"this":[76],"paper,":[77],"we":[78,133,198],"propose":[79],"use":[81],"an":[82],"encoder":[83],"with":[84,166,176],"simpler":[86],"structure,":[88],"called":[89],"dual-branch":[91,208],"attention":[92,108,209],"module":[93,96,210],"(DBAM).":[94],"improved":[98],"based":[99],"conformer":[102],"using":[103],"two":[104,152,163],"parallel":[105],"branches":[106],"convolution,":[110],"can":[112,144,160],"model":[113],"both":[114],"global":[115],"local":[117],"contextual":[118],"information.":[119],"We":[120,174],"also":[121],"blend":[122],"low-level":[123],"high-level":[125],"features":[126],"task.":[130],"addition,":[132],"add":[134],"soft":[135,212],"parameter":[136,213],"sharing":[137],"joint":[140],"network,":[142],"efficiently":[145],"exploit":[146],"potential":[148],"relationship":[149],"between":[150],"subtasks,":[153],"SED":[154],"DOA.":[156],"proposed":[158,187],"method":[159,188],"effectively":[161],"detect":[162],"events":[165],"overlapping":[167],"occurrence":[168],"same":[171],"period.":[173],"experimented":[175],"open":[178],"dataset":[179],"DCASE":[180],"2020":[181],"3":[183],"proving":[184],"that":[185],"better":[190],"than":[193],"baseline":[195],"model.":[196],"Furthermore,":[197],"conducted":[199],"ablation":[200],"experiments":[201],"for":[202],"verifying":[203],"effectiveness":[205],"sharing.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}