{"id":"https://openalex.org/W2015293542","doi":"https://doi.org/10.1145/1631272.1631301","title":"Visual speaker localization aided by acoustic models","display_name":"Visual speaker localization aided by acoustic models","publication_year":2009,"publication_date":"2009-10-19","ids":{"openalex":"https://openalex.org/W2015293542","doi":"https://doi.org/10.1145/1631272.1631301","mag":"2015293542"},"language":"en","primary_location":{"id":"doi:10.1145/1631272.1631301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/145992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028054905","display_name":"Chuohao Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuohao Yeo","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061353073","display_name":"Hayley Hung","orcid":"https://orcid.org/0000-0001-9574-5395"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hayley Hung","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3577,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95760747,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music 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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.913019597530365},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8193963766098022},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7275295257568359},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6521221995353699},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5823583602905273},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5649462342262268},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5624299645423889},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49027279019355774},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42752766609191895},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42144858837127686},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41097304224967957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40222403407096863},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11390864849090576},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08294782042503357}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.913019597530365},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193963766098022},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7275295257568359},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6521221995353699},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5823583602905273},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5649462342262268},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5624299645423889},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49027279019355774},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42752766609191895},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42144858837127686},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41097304224967957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40222403407096863},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11390864849090576},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08294782042503357},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1631272.1631301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:145992","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145992","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:145992","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145992","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W341184420","https://openalex.org/W1583620810","https://openalex.org/W1587845029","https://openalex.org/W1978348414","https://openalex.org/W1988074515","https://openalex.org/W1991048564","https://openalex.org/W2015394094","https://openalex.org/W2033966334","https://openalex.org/W2073711670","https://openalex.org/W2096258226","https://openalex.org/W2098923380","https://openalex.org/W2099403067","https://openalex.org/W2106488367","https://openalex.org/W2113386290","https://openalex.org/W2114032116","https://openalex.org/W2115175902","https://openalex.org/W2118847468","https://openalex.org/W2123921937","https://openalex.org/W2124673517","https://openalex.org/W2125336414","https://openalex.org/W2144125830","https://openalex.org/W2153801342","https://openalex.org/W2167709189","https://openalex.org/W2306409666","https://openalex.org/W2338994564","https://openalex.org/W4231379535","https://openalex.org/W4300482596","https://openalex.org/W6659344013"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"The":[0,56,92,109],"following":[1],"paper":[2],"presents":[3],"a":[4,15,22,26,51,74,125],"novel":[5],"audio-visual":[6,116],"approach":[7],"for":[8],"unsupervised":[9,53],"speaker":[10,30,35,57,128,134],"locationing.":[11],"Using":[12],"recordings":[13],"from":[14],"single,":[16],"low-resolution":[17],"room":[18],"overview":[19],"camera":[20],"and":[21,43,67,140],"single":[23],"far-field":[24],"microphone,":[25],"state-of-the":[27],"art":[28],"audio-only":[29],"localization":[31],"system":[32,59,111],"(traditionally":[33],"called":[34],"diarization)":[36],"is":[37,112],"extended":[38],"so":[39],"that":[40],"both":[41],"acoustic":[42],"visual":[44,78,133],"models":[45,79],"are":[46,80],"estimated":[47],"as":[48],"part":[49],"of":[50,65,86,102,124],"joint":[52],"optimization":[54],"problem.":[55],"diarization":[58],"first":[60],"automatically":[61],"determines":[62],"the":[63,77,84,87,90,103,122],"number":[64],"speakers":[66,88],"estimates":[68],"\"who":[69],"spoke":[70],"when\",":[71],"then,":[72],"in":[73,89],"second":[75],"step,":[76],"used":[81],"to":[82,114,118],"infer":[83],"location":[85],"video.":[91],"experiments":[93],"were":[94],"performed":[95],"on":[96],"real-world":[97],"meetings":[98],"using":[99],"4.5":[100],"hours":[101],"publicly":[104],"available":[105],"AMI":[106],"meeting":[107],"corpus.":[108],"proposed":[110],"able":[113],"exploit":[115],"integration":[117],"not":[119],"only":[120],"improve":[121],"accuracy":[123],"state-of-the-art":[126],"(audio-only)":[127],"diarization,":[129],"but":[130],"also":[131],"adds":[132],"locationing":[135],"at":[136],"little":[137],"incremental":[138],"engineering":[139],"computation":[141],"costs.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
