{"id":"https://openalex.org/W2115878730","doi":"https://doi.org/10.1145/1865106.1865111","title":"Dialocalization","display_name":"Dialocalization","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2115878730","doi":"https://doi.org/10.1145/1865106.1865111","mag":"2115878730"},"language":"en","primary_location":{"id":"doi:10.1145/1865106.1865111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1865106.1865111","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/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":true,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA","International Computer Science Institute, Berkeley, CA,#TAB#"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA,#TAB#","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/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chuohao Yeo","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062323483"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":3.08,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92147098,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"18"},"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":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9937000274658203,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8611974716186523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8128129243850708},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6911436319351196},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6039660573005676},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5945875644683838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5876702070236206},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.578752338886261},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.556710958480835},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49345508217811584},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4836946129798889},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4389099180698395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4281715154647827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10655194520950317},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09300991892814636},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07740294933319092}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8611974716186523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128129243850708},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6911436319351196},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6039660573005676},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5945875644683838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5876702070236206},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.578752338886261},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.556710958480835},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49345508217811584},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4836946129798889},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4389099180698395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4281715154647827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10655194520950317},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09300991892814636},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07740294933319092},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1865106.1865111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1865106.1865111","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/c6481f56-c1ce-498f-9007-a6694ac21e39","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/dialocalization-acoustic-speaker-diarization-and-visual-localization-as-joint-optimization-problem(c6481f56-c1ce-498f-9007-a6694ac21e39).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Friedland, G, Yeo, C & Hung, H 2010, 'Dialocalization: Acoustic speaker diarization and visual localization as joint optimization problem', ACM Transactions on Multimedia Computing Communications and Applications, vol. 6, no. 4, pp. 27. https://doi.org/10.1145/1865106.1865111","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/c6481f56-c1ce-498f-9007-a6694ac21e39","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/dialocalization-acoustic-speaker-diarization-and-visual-localization-as-joint-optimization-problem(c6481f56-c1ce-498f-9007-a6694ac21e39).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Friedland, G, Yeo, C & Hung, H 2010, 'Dialocalization: Acoustic speaker diarization and visual localization as joint optimization problem', ACM Transactions on Multimedia Computing Communications and Applications, vol. 6, no. 4, pp. 27. https://doi.org/10.1145/1865106.1865111","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W341184420","https://openalex.org/W641890772","https://openalex.org/W1482605500","https://openalex.org/W1554595927","https://openalex.org/W1581253957","https://openalex.org/W1583620810","https://openalex.org/W1587845029","https://openalex.org/W1603895355","https://openalex.org/W1978348414","https://openalex.org/W1988074515","https://openalex.org/W1991048564","https://openalex.org/W2009355432","https://openalex.org/W2015293542","https://openalex.org/W2015394094","https://openalex.org/W2024991751","https://openalex.org/W2033966334","https://openalex.org/W2035379092","https://openalex.org/W2036365100","https://openalex.org/W2048447221","https://openalex.org/W2073711670","https://openalex.org/W2096258226","https://openalex.org/W2097369932","https://openalex.org/W2098923380","https://openalex.org/W2099403067","https://openalex.org/W2103621378","https://openalex.org/W2106488367","https://openalex.org/W2113386290","https://openalex.org/W2114032116","https://openalex.org/W2114701396","https://openalex.org/W2115175902","https://openalex.org/W2118847468","https://openalex.org/W2123008134","https://openalex.org/W2123921937","https://openalex.org/W2124673517","https://openalex.org/W2125336414","https://openalex.org/W2136145761","https://openalex.org/W2137479423","https://openalex.org/W2138414774","https://openalex.org/W2144125830","https://openalex.org/W2148882869","https://openalex.org/W2164512637","https://openalex.org/W2167709189","https://openalex.org/W2169264834","https://openalex.org/W2236842960","https://openalex.org/W2306409666","https://openalex.org/W2488097972","https://openalex.org/W2980286501","https://openalex.org/W3143835353","https://openalex.org/W4301005547","https://openalex.org/W6611547243"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2769861442","https://openalex.org/W2162158162","https://openalex.org/W1980506188","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021"],"abstract_inverted_index":{"The":[0,66,106,123,157,177],"following":[1],"article":[2,178],"presents":[3,182],"a":[4,26,33,37,61,83,139],"novel":[5],"audio-visual":[6,130],"approach":[7],"for":[8],"unsupervised":[9,63],"speaker":[10,40,67,142,148],"localization":[11,44,149],"in":[12,45,82,98,171],"both":[13,51],"time":[14],"and":[15,17,32,53,76,154,188],"space":[16],"systematically":[18,189],"analyzes":[19],"its":[20,186],"unique":[21],"properties.":[22],"Using":[23],"recordings":[24],"from":[25],"single,":[27],"low-resolution":[28],"room":[29],"overview":[30],"camera":[31],"single":[34,175],"far-field":[35],"microphone,":[36],"state-of-the-art":[38,140],"audio-only":[39],"diarization":[41,68],"system":[42,69,125],"(speaker":[43],"time)":[46],"is":[47,126],"extended":[48],"so":[49],"that":[50,167],"acoustic":[52],"visual":[54,87,147],"models":[55,88],"are":[56,89],"estimated":[57],"as":[58,164],"part":[59],"of":[60,95,116,138,193],"joint":[62],"optimization":[64],"problem.":[65],"first":[70],"automatically":[71],"determines":[72],"the":[73,86,93,96,99,117,136,180,191],"speech":[74],"regions":[75],"estimates":[77],"\u201cwho":[78],"spoke":[79],"when,\u201d":[80],"then,":[81],"second":[84],"step,":[85],"used":[90],"to":[91,128,132],"infer":[92],"location":[94],"speakers":[97],"video.":[100],"We":[101],"call":[102],"this":[103],"process":[104],"\u201cdialocalization.\u201d":[105],"experiments":[107],"were":[108],"performed":[109],"on":[110,174],"real-world":[111],"meetings":[112],"using":[113],"4.5":[114],"hours":[115],"publicly":[118],"available":[119],"AMI":[120],"meeting":[121],"corpus.":[122],"proposed":[124],"able":[127],"exploit":[129],"integration":[131],"not":[133],"only":[134],"improve":[135],"accuracy":[137],"(audio-only)":[141],"diarization,":[143],"but":[144],"also":[145],"adds":[146],"at":[150],"little":[151],"incremental":[152],"engineering":[153],"computation":[155],"costs.":[156],"combined":[158],"algorithm":[159],"has":[160],"different":[161],"properties,":[162,187],"such":[163],"increased":[165],"robustness,":[166],"cannot":[168],"be":[169],"observed":[170],"algorithms":[172],"based":[173],"modalities.":[176],"describes":[179],"algorithm,":[181],"benchmarking":[183],"results,":[184],"explains":[185],"discusses":[190],"contributions":[192],"each":[194],"modality.":[195]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2016-06-24T00:00:00"}
