{"id":"https://openalex.org/W821576326","doi":"https://doi.org/10.21437/interspeech.2014-145","title":"Diarizing large corpora using multi-modal speaker linking","display_name":"Diarizing large corpora using multi-modal speaker linking","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W821576326","doi":"https://doi.org/10.21437/interspeech.2014-145","mag":"821576326"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-145","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publica.fraunhofer.de/documents/N-351238.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027284390","display_name":"Marc Ferr\u00e0s","orcid":null},"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":"Marc Ferr\u00e0s","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025911155","display_name":"Stefano Masneri","orcid":"https://orcid.org/0000-0003-1965-5704"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefano Masneri","raw_affiliation_strings":["Fraunhofer Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Society","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049085567","display_name":"Oliver Schreer","orcid":"https://orcid.org/0000-0001-6900-8287"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Schreer","raw_affiliation_strings":["Fraunhofer Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Society","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"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":"Herv\u00e9 Bourlard","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2687,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84005606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"602","last_page":"606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824991941452026},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7077575325965881},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49169427156448364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4236403703689575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35032132267951965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824991941452026},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7077575325965881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49169427156448364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4236403703689575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35032132267951965},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2014-145","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-351238","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-351238.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer HHI","raw_type":"Conference Paper"},{"id":"pmh:oai:infoscience.epfl.ch:203852","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/203852","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"},{"id":"pmh:oai:publica.fraunhofer.de:publica/387556","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/387556","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:fraunhofer.de:N-351238","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-351238.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer HHI","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1545641654","https://openalex.org/W2007995029","https://openalex.org/W2016381774","https://openalex.org/W2063511145","https://openalex.org/W2098693229","https://openalex.org/W2098726438","https://openalex.org/W2115599677","https://openalex.org/W2116019577","https://openalex.org/W2121415728","https://openalex.org/W2126237829","https://openalex.org/W2136879537","https://openalex.org/W2141660036","https://openalex.org/W2142333570","https://openalex.org/W2180187800","https://openalex.org/W2397770179"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,54,57,139],"of":[2,5,41,107,135,148],"a":[3,12,48],"collection":[4],"recordings":[6],"with":[7],"uniquely":[8],"identified":[9],"speakers":[10,95],"is":[11,33,112],"challenging":[13],"task.":[14],"A":[15],"system":[16,65,111],"addressing":[17],"such":[18],"task":[19],"must":[20],"account":[21],"for":[22,118],"the":[23,78,82,105,108,115,119,146],"inter-session":[24],"variability":[25],"present":[26],"from":[27],"recording":[28,30],"to":[29,35,38,51,93,103,144,152],"and":[31,58,81,100,137],"it":[32],"asked":[34],"scale":[36,155],"well":[37],"massive":[39],"amounts":[40],"data.":[42],"In":[43],"this":[44,91],"paper":[45],"we":[46],"use":[47],"two-stage":[49],"approach":[50],"corpus-wide":[52],"speaker":[53,56,59,63,68,150,156],"involving":[55,125],"linking":[60,64,151],"stages.":[61],"The":[62,110],"agglomeratively":[66],"clusters":[67],"factor":[69],"posterior":[70],"distributions":[71],"obtained":[72],"via":[73],"Joint":[74],"Factor":[75],"Analysis":[76],"using":[77,114],"Ward":[79],"method":[80],"Hotteling":[83],"t-square":[84],"statistic":[85],"as":[86],"distance":[87],"measure.":[88],"We":[89,130],"extend":[90],"framework":[92],"link":[94],"based":[96],"on":[97],"both":[98],"speech":[99],"visual":[101],"modalities":[102],"improve":[104],"robustness":[106],"system.":[109],"evaluated":[113],"data":[116],"collected":[117],"Augmented":[120],"Multiparty":[121],"Interaction":[122],"(AMI)":[123],"project,":[124],"over":[126],"one":[127],"hundred":[128],"meetings.":[129],"provide":[131],"results":[132],"in":[133],"terms":[134],"within-recording":[136],"across-recording":[138],"error":[140],"rates":[141],"(DER":[142],")":[143],"support":[145],"effectiveness":[147],"multi-modal":[149],"enable":[153],"large":[154],"diarization.":[157]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
