{"id":"https://openalex.org/W4392904168","doi":"https://doi.org/10.1109/icassp48485.2024.10448050","title":"Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection","display_name":"Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904168","doi":"https://doi.org/10.1109/icassp48485.2024.10448050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448050","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/A5005679652","display_name":"Davide Berghi","orcid":"https://orcid.org/0000-0001-6279-6364"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Davide Berghi","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050479982","display_name":"Peipei Wu","orcid":"https://orcid.org/0009-0006-4551-3223"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peipei Wu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057816329","display_name":"Jinzheng Zhao","orcid":"https://orcid.org/0009-0004-3910-850X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinzheng Zhao","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005679652"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":3.9508,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94324324,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8816","last_page":"8820"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9811999797821045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7895824909210205},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7810813784599304},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7227928638458252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6297953128814697},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6151300668716431},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6116737723350525},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5615024566650391},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4839494526386261},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.46769264340400696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45590680837631226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4206274747848511},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4178304672241211},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4158511459827423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17253372073173523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895824909210205},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7810813784599304},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7227928638458252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297953128814697},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6151300668716431},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6116737723350525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5615024566650391},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4839494526386261},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.46769264340400696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45590680837631226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4206274747848511},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4178304672241211},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4158511459827423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17253372073173523},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448050","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2810934215","https://openalex.org/W2942551338","https://openalex.org/W2963524571","https://openalex.org/W2982382207","https://openalex.org/W3097777922","https://openalex.org/W3098454764","https://openalex.org/W3163881933","https://openalex.org/W3203177955","https://openalex.org/W3206329344","https://openalex.org/W3213455868","https://openalex.org/W4225270933","https://openalex.org/W4312367758","https://openalex.org/W4324116353","https://openalex.org/W4380994299","https://openalex.org/W4387929435","https://openalex.org/W4401342172","https://openalex.org/W6739901393","https://openalex.org/W6838853441","https://openalex.org/W6853532597","https://openalex.org/W6857606499","https://openalex.org/W6870796758"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Sound":[0],"event":[1,10],"localization":[2],"and":[3,13,41,61,77,91,106,142],"detection":[4,11],"(SELD)":[5],"combines":[6],"two":[7],"subtasks:":[8],"sound":[9],"(SED)":[12],"direction":[14],"of":[15,59,84,117,127],"arrival":[16],"(DOA)":[17],"estimation.":[18],"SELD":[19],"is":[20],"usually":[21],"tackled":[22],"as":[23,148],"an":[24],"audio-only":[25,105],"problem,":[26],"but":[27],"visual":[28,62,72],"information":[29],"has":[30],"been":[31,39],"recently":[32],"included.":[33],"Few":[34],"audio-visual":[35],"(AV)-SELD":[36],"works":[37],"have":[38],"published":[40],"most":[42],"employ":[43],"vision":[44],"via":[45],"face/object":[46],"bounding":[47],"boxes,":[48],"or":[49,137],"human":[50],"pose":[51],"keypoints.":[52],"In":[53],"contrast,":[54],"we":[55,74],"explore":[56],"the":[57,71,89,101,114,118,128],"integration":[58],"audio":[60],"feature":[63],"embeddings":[64],"extracted":[65],"with":[66],"pre-trained":[67],"deep":[68],"networks.":[69],"For":[70],"modality,":[73],"tested":[75],"ResNet50":[76],"Inflated":[78],"3D":[79],"ConvNet":[80],"(I3D).":[81],"Our":[82,97],"comparison":[83],"AV":[85,107,129],"fusion":[86],"methods":[87],"includes":[88],"AV-Conformer":[90],"Cross-Modal":[92],"Attentive":[93],"Fusion":[94],"(CMAF)":[95],"model.":[96],"best":[98],"models":[99],"outperform":[100],"DCASE":[102],"2023":[103],"Task3":[104],"baselines":[108],"by":[109],"a":[110],"wide":[111],"margin":[112],"on":[113],"development":[115],"set":[116],"STARSS23":[119],"dataset,":[120],"making":[121],"them":[122],"competitive":[123],"amongst":[124],"state-of-the-art":[125],"results":[126],"challenge,":[130],"without":[131],"model":[132],"ensembling,":[133],"heavy":[134],"data":[135],"augmentation,":[136],"prediction":[138],"post-processing.":[139],"Such":[140],"techniques":[141],"further":[143],"pre-training":[144],"could":[145],"be":[146],"applied":[147],"next":[149],"steps":[150],"to":[151],"improve":[152],"performance.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}