{"id":"https://openalex.org/W4297841792","doi":"https://doi.org/10.21437/interspeech.2022-10670","title":"Visually-aware Acoustic Event Detection using Heterogeneous Graphs","display_name":"Visually-aware Acoustic Event Detection using Heterogeneous Graphs","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841792","doi":"https://doi.org/10.21437/interspeech.2022-10670"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10670","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10670","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/64858.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011875948","display_name":"AMIR SHIRIAN","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"AMIR SHIRIAN","raw_affiliation_strings":["The University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["Google Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634965","display_name":"V\u00edctor S\u00e1nchez","orcid":"https://orcid.org/0000-0002-7089-7031"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victor Sanchez","raw_affiliation_strings":["The University of Warwick, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Warwick, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021354054","display_name":"Tanaya Guha","orcid":"https://orcid.org/0000-0003-2167-4891"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tanaya Guha","raw_affiliation_strings":["The University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"2428","last_page":"2432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9972000122070312,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8210340738296509},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.601284921169281},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5310566425323486},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5100632309913635},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4905978739261627},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43900197744369507},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4388415515422821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42547327280044556},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41532260179519653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3954850435256958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32175713777542114},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25094324350357056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210340738296509},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.601284921169281},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5310566425323486},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5100632309913635},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4905978739261627},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43900197744369507},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4388415515422821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42547327280044556},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41532260179519653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3954850435256958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32175713777542114},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25094324350357056},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-10670","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10670","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:276564","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/64858.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},{"id":"pmh:oai:wrap.warwick.ac.uk:166888","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Item"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:276564","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/64858.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2015394094","https://openalex.org/W2526050071","https://openalex.org/W2529337537","https://openalex.org/W2575911703","https://openalex.org/W2593116425","https://openalex.org/W2773514261","https://openalex.org/W2890052321","https://openalex.org/W2962711740","https://openalex.org/W2964015378","https://openalex.org/W2990408345","https://openalex.org/W3004507689","https://openalex.org/W3012871709","https://openalex.org/W3037195468","https://openalex.org/W3037309139","https://openalex.org/W3081360282","https://openalex.org/W3093563057","https://openalex.org/W3094123278","https://openalex.org/W3094454579","https://openalex.org/W3094550259","https://openalex.org/W3105009590","https://openalex.org/W3123709248","https://openalex.org/W3127694567","https://openalex.org/W3130206595","https://openalex.org/W3134652006","https://openalex.org/W3145385912","https://openalex.org/W3154596443","https://openalex.org/W3162322471","https://openalex.org/W3173025631","https://openalex.org/W3174517569","https://openalex.org/W3176349206","https://openalex.org/W3196974791","https://openalex.org/W3209483675","https://openalex.org/W3210733870","https://openalex.org/W4205091644","https://openalex.org/W4285414370","https://openalex.org/W4287726044","https://openalex.org/W4297733535","https://openalex.org/W4297841641"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2378211422","https://openalex.org/W2988126442","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W1974414866","https://openalex.org/W2130974462"],"abstract_inverted_index":{"Perception":[0],"of":[1,17,70,90,99,119],"auditory":[2],"events":[3,120],"is":[4,139],"inherently":[5],"multimodal":[6,19],"relying":[7],"on":[8,125],"both":[9,104],"audio":[10],"and":[11,27,48,54,81,101,107],"visual":[12],"cues.":[13],"A":[14],"large":[15,128],"number":[16],"existing":[18],"approaches":[20,65],"process":[21],"each":[22],"modality":[23],"using":[24],"modality-specific":[25],"models":[26],"then":[28],"fuse":[29],"the":[30,34,46,52,59,68,88],"embeddings":[31],"to":[32,43,66,84,116],"encode":[33],"joint":[35],"information.":[36],"In":[37],"contrast,":[38],"we":[39,95],"employ":[40],"heterogeneous":[41,63,93],"graphs":[42],"explicitly":[44],"capture":[45],"spatial":[47,106],"temporal":[49,108],"relationships":[50,103],"between":[51],"modalities":[53],"represent":[55,85],"detailed":[56],"information":[57],"about":[58],"underlying":[60],"signal.":[61],"Using":[62],"graph":[64],"address":[67],"task":[69],"visually-aware":[71],"acoustic":[72],"event":[73],"classification,":[74],"which":[75],"serves":[76],"as":[77],"a":[78,127],"compact,":[79],"efficient":[80],"scalable":[82],"way":[83],"data":[86],"in":[87],"form":[89],"graphs.":[91],"Through":[92],"graphs,":[94],"show":[96],"efficiently":[97],"modelling":[98],"intra-":[100],"inter-modality":[102],"at":[105,141],"scales.":[109],"Our":[110,137],"model":[111,133],"can":[112],"easily":[113],"be":[114],"adapted":[115],"different":[117],"scales":[118],"through":[121],"relevant":[122],"hyperparameters.":[123],"Experiments":[124],"AudioSet,":[126],"benchmark,":[129],"shows":[130],"that":[131],"our":[132],"achieves":[134],"state-of-the-art":[135],"performance.":[136],"code":[138],"available":[140],"github.com/AmirSh15/VAED":[142],"HeterGraph.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-10-01T00:00:00"}