{"id":"https://openalex.org/W4415709487","doi":"https://doi.org/10.1109/icme59968.2025.11210191","title":"Location-Oriented Sound Event Localization and Detection with Spatial Mapping and Regression Localization","display_name":"Location-Oriented Sound Event Localization and Detection with Spatial Mapping and Regression Localization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709487","doi":"https://doi.org/10.1109/icme59968.2025.11210191"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109611898","display_name":"Xueping Zhang","orcid":"https://orcid.org/0009-0008-8055-819X"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueping Zhang","raw_affiliation_strings":["Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China,430070"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China,430070","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003775716","display_name":"Yaxiong Chen","orcid":"https://orcid.org/0000-0002-2903-6723"},"institutions":[{"id":"https://openalex.org/I4210149102","display_name":"Sanya University","ror":"https://ror.org/04fa2qd52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149102"]},{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Chen","raw_affiliation_strings":["Wuhan University of Technology,Sanya Science and Education Innovation Park,Sanya,China,572000"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,Sanya Science and Education Innovation Park,Sanya,China,572000","institution_ids":["https://openalex.org/I4210149102","https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053695187","display_name":"Ruilin Yao","orcid":"https://orcid.org/0009-0002-6654-2294"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruilin Yao","raw_affiliation_strings":["Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China,430070"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China,430070","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086323231","display_name":"Yunfei Zi","orcid":"https://orcid.org/0000-0002-4778-7109"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Zi","raw_affiliation_strings":["Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China,430070"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer Science and Artificial Intelligence,Wuhan,China,430070","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011707621","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-4006-7029"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I4210149102","display_name":"Sanya University","ror":"https://ror.org/04fa2qd52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwu Xiong","raw_affiliation_strings":["Wuhan University of Technology,Sanya Science and Education Innovation Park,Sanya,China,572000"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,Sanya Science and Education Innovation Park,Sanya,China,572000","institution_ids":["https://openalex.org/I4210149102","https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109611898"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39646218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9642000198364258,"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":0.9642000198364258,"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":0.027899999171495438,"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":0.0020000000949949026,"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/event","display_name":"Event (particle physics)","score":0.7063999772071838},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6834999918937683},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6510000228881836},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5105000138282776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.36340001225471497}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7063999772071838},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6834999918937683},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5884000062942505},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2987896495","wikidata":"https://www.wikidata.org/wiki/Q5416716","display_name":"Event data","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11210191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.48550/arxiv.2504.08365","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2504.08365","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2130640900","https://openalex.org/W2135131618","https://openalex.org/W2160557558","https://openalex.org/W2460742184","https://openalex.org/W2592109325","https://openalex.org/W2745195618","https://openalex.org/W2810934215","https://openalex.org/W2884367402","https://openalex.org/W2951942899","https://openalex.org/W2982680886","https://openalex.org/W3005741390","https://openalex.org/W3083274258","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3178592608","https://openalex.org/W3206329344","https://openalex.org/W4307823382","https://openalex.org/W4320002812","https://openalex.org/W4324116353","https://openalex.org/W4360584650","https://openalex.org/W4372260505","https://openalex.org/W4385822682","https://openalex.org/W4388820715","https://openalex.org/W4390112990","https://openalex.org/W4391235393","https://openalex.org/W4394625773"],"related_works":[],"abstract_inverted_index":{"Sound":[0,8],"Event":[1,9],"Localization":[2,52],"and":[3,50,68,123,126,138],"Detection":[4,10],"(SELD)":[5],"combines":[6],"the":[7,13,25,32,35,41,58,78,82,85,92,102,105,113,131],"(SED)":[11],"with":[12],"corresponding":[14,86],"Direction":[15],"Of":[16],"Arrival":[17],"(DOA).":[18],"Recently,":[19],"adopted":[20],"event-oriented":[21],"multi-track":[22],"methods":[23,134],"affect":[24],"generality":[26,42],"in":[27,43,135],"polyphonic":[28,44,109],"environments":[29],"due":[30],"to":[31,64,76,94,107],"limitation":[33],"of":[34,37,84,112,115],"number":[36,114],"tracks.":[38],"To":[39],"enhance":[40],"environments,":[45],"we":[46],"propose":[47],"Spatial":[48],"Mapping":[49],"Regression":[51],"for":[53],"SELD":[54,133],"(SMRL-SELD).":[55],"SMRL-SELD":[56,88,129],"segments":[57],"3D":[59],"spatial":[60],"space,":[61],"mapping":[62],"it":[63],"a":[65,69],"2D":[66],"plane,":[67],"new":[70],"regression":[71],"localization":[72],"loss":[73],"is":[74,89],"proposed":[75,128],"help":[77],"results":[79],"converge":[80],"toward":[81],"location":[83],"event.":[87],"location-oriented,":[90],"allowing":[91],"model":[93,106],"learn":[95],"event":[96],"features":[97],"based":[98],"on":[99,121],"orientation.":[100],"Thus,":[101],"method":[103],"enables":[104],"process":[108],"sounds":[110],"regardless":[111],"overlapping":[116],"events.":[117],"We":[118],"conducted":[119],"experiments":[120],"STARSS23":[122],"STARSS22":[124],"datasets":[125],"our":[127],"outperforms":[130],"existing":[132],"overall":[136],"evaluation":[137],"polyphony":[139],"environments.":[140]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-30T00:00:00"}
