{"id":"https://openalex.org/W3091224032","doi":null,"title":"A method for evaluating audio-visual scene analysis in multi-talker environments","display_name":"A method for evaluating audio-visual scene analysis in multi-talker environments","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3091224032","mag":"3091224032"},"language":"en","primary_location":{"id":"mag:3091224032","doi":null,"is_oa":false,"landing_page_url":"https://backend.orbit.dtu.dk/ws/files/213378581/420_Article_PDF_file_2830_1_10_20200429.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5052839476","display_name":"Kasper Duemose Lund","orcid":"https://orcid.org/0000-0003-2559-7694","observed_orcids":["https://orcid.org/0000-0003-2559-7694"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Kasper Duemose Lund","raw_affiliation_strings":["Hearing Systems Group","Technical University of Denmark, Department of Health Technology, DK"],"raw_orcid":"https://orcid.org/0000-0003-2559-7694","affiliations":[{"raw_affiliation_string":"Hearing Systems Group","institution_ids":[]},{"raw_affiliation_string":"Technical University of Denmark, Department of Health Technology, DK","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008808116","display_name":"Axel Ahrens","orcid":"https://orcid.org/0000-0001-8800-2497","observed_orcids":["https://orcid.org/0000-0001-8800-2497"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Axel Ahrens","raw_affiliation_strings":["Hearing Systems Group","Technical University of Denmark, Department of Health Technology, DK"],"raw_orcid":"https://orcid.org/0000-0001-8800-2497","affiliations":[{"raw_affiliation_string":"Hearing Systems Group","institution_ids":[]},{"raw_affiliation_string":"Technical University of Denmark, Department of Health Technology, DK","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046255570","display_name":"Torsten Dau","orcid":"https://orcid.org/0000-0001-8110-4343","observed_orcids":["https://orcid.org/0000-0001-8110-4343"]},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Torsten Dau","raw_affiliation_strings":["Hearing Systems Group","Technical University of Denmark, Department of Health Technology, DK"],"raw_orcid":"https://orcid.org/0000-0001-8110-4343","affiliations":[{"raw_affiliation_string":"Hearing Systems Group","institution_ids":[]},{"raw_affiliation_string":"Technical University of Denmark, Department of Health Technology, DK","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5052839476"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":0.2698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51732582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.948199987411499,"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/T10860","display_name":"Speech and Audio Processing","score":0.948199987411499,"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/T12032","display_name":"Multisensory perception and integration","score":0.01119999960064888,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.008999999612569809,"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/cocktail-party-problem","display_name":"cocktail party problem","score":0.7820000052452087},{"id":"https://openalex.org/keywords/source-localization","display_name":"source localization","score":0.5559999942779541},{"id":"https://openalex.org/keywords/speech-perception","display_name":"speech perception","score":0.35499998927116394},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"virtual reality","score":0.7429999709129333},{"id":"https://openalex.org/keywords/virtual-acoustics","display_name":"virtual acoustics","score":0.9610000252723694},{"id":"https://openalex.org/keywords/talker-identification","display_name":"talker identification","score":0.5109999775886536}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7969974279403687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6368303298950195},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4657405614852905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44106024503707886},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42889225482940674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40834060311317444},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3413984775543213},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24537751078605652},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.1856025755405426},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.12444856762886047},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.06517192721366882}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3091224032","doi":null,"is_oa":false,"landing_page_url":"https://backend.orbit.dtu.dk/ws/files/213378581/420_Article_PDF_file_2830_1_10_20200429.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1964538581","https://openalex.org/W1986665977","https://openalex.org/W2057851139","https://openalex.org/W2087919634","https://openalex.org/W2494015126","https://openalex.org/W2913474996","https://openalex.org/W2951033593","https://openalex.org/W3124666641"],"related_works":["https://openalex.org/W2996639980","https://openalex.org/W4295136605","https://openalex.org/W6906836698","https://openalex.org/W3196777808","https://openalex.org/W2886975344","https://openalex.org/W4401633522","https://openalex.org/W4411191681","https://openalex.org/W2013354643","https://openalex.org/W2624341483","https://openalex.org/W7160414477"],"abstract_inverted_index":{"In":[0],"cocktail-party":[1,30],"environments,":[2],"listeners":[3],"are":[4],"able":[5],"to":[6,26,72,77,107,138,142],"comprehend":[7],"and":[8,19,47,53,80,124],"localize":[9],"multiple":[10],"simultaneous":[11],"talkers.":[12,91],"With":[13,92,130],"current":[14],"virtual":[15,20],"reality":[16],"(VR)":[17],"technology":[18],"acoustics":[21],"it":[22],"has":[23],"become":[24],"possible":[25],"present":[27],"an":[28,63,93],"audio-visual":[29,145],"in":[31,67,101,115],"a":[32,58,116,133],"controlled":[33],"laboratory":[34],"environment.":[35],"A":[36],"new":[37,134],"continuous":[38],"speech":[39],"corpus":[40],"with":[41],"ten":[42],"monologues":[43],"from":[44],"five":[45,48],"female":[46],"male":[49],"talkers":[50,75,113,121],"was":[51,105,122],"designed":[52],"recorded.":[54],"Each":[55],"monologue":[56],"contained":[57],"substantially":[59],"different":[60],"topic.":[61],"Using":[62],"egocentric":[64],"interaction":[65],"method":[66],"VR,":[68],"subjects":[69],"were":[70,114],"asked":[71],"label":[73],"perceived":[74],"according":[76],"source":[78],"position":[79],"content":[81],"of":[82,88,96,120],"speech,":[83],"while":[84],"varying":[85],"the":[86,98,118,125],"number":[87,95,119],"simultaneously":[89],"presented":[90,137],"increasing":[94],"talkers,":[97],"subjects\u2019":[99],"accuracy":[100],"performing":[102],"this":[103,131],"task":[104],"found":[106],"decrease.":[108],"When":[109],"more":[110],"than":[111],"six":[112],"scene,":[117],"underestimated":[123],"azimuth":[126],"localization":[127],"error":[128],"increased.":[129],"method,":[132],"approach":[135],"is":[136],"gauge":[139],"listeners\u2019":[140],"ability":[141],"analyze":[143],"complex":[144],"scenes.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2020-10-08T00:00:00"}