{"id":"https://openalex.org/W2403232117","doi":"https://doi.org/10.1109/icassp.2016.7472743","title":"OCR-aided person annotation and label propagation for speaker modeling in TV shows","display_name":"OCR-aided person annotation and label propagation for speaker modeling in TV shows","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2403232117","doi":"https://doi.org/10.1109/icassp.2016.7472743","mag":"2403232117"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01350071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028277047","display_name":"Mateusz Budnik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mateusz Budnik","raw_affiliation_strings":["Laboratoire d'Informatique de Grenoble, Univ. Grenoble-Alpes, Grenoble, France","Laboratoire d'Informatique de Grenoble"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Grenoble, Univ. Grenoble-Alpes, Grenoble, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Laboratoire d'Informatique de Grenoble","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040820339","display_name":"Laurent Besacier","orcid":"https://orcid.org/0000-0001-7411-9125"},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I185839726","display_name":"Institut Universitaire de France","ror":"https://ror.org/055khg266","country_code":"FR","type":"education","lineage":["https://openalex.org/I185839726"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Besacier","raw_affiliation_strings":["Laboratoire d'Informatique de Grenoble, Univ. Grenoble-Alpes, Grenoble, France","Institut Universitaire de France","Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Grenoble, Univ. Grenoble-Alpes, Grenoble, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Institut Universitaire de France","institution_ids":["https://openalex.org/I185839726"]},{"raw_affiliation_string":"Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072054157","display_name":"Ali Khodabakhsh","orcid":"https://orcid.org/0000-0002-2873-4140"},"institutions":[{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["FR","TR"],"is_corresponding":false,"raw_author_name":"Ali Khodabakhsh","raw_affiliation_strings":["Electrical and Computer Engineering Department, Ozyegin University, Istanbul, Turkey","Istanbul University","Laboratoire d'Informatique de Grenoble"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Istanbul University","institution_ids":["https://openalex.org/I67581229"]},{"raw_affiliation_string":"Laboratoire d'Informatique de Grenoble","institution_ids":["https://openalex.org/I4210104430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016845689","display_name":"Cenk Demiro\u011flu","orcid":"https://orcid.org/0000-0002-6160-3169"},"institutions":[{"id":"https://openalex.org/I67581229","display_name":"Istanbul University","ror":"https://ror.org/03a5qrr21","country_code":"TR","type":"education","lineage":["https://openalex.org/I67581229"]},{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cenk Demiroglu","raw_affiliation_strings":["Electrical and Computer Engineering Department, Ozyegin University, Istanbul, Turkey","Istanbul University"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Istanbul University","institution_ids":["https://openalex.org/I67581229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028277047"],"corresponding_institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I899635006"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03883095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":null,"first_page":"5570","last_page":"5574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8480966687202454},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8105782270431519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6478408575057983},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.626213014125824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5613347887992859},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5296216607093811},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4929053783416748},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4615592360496521},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4501835107803345},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4333399534225464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43259376287460327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4268079996109009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480966687202454},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8105782270431519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478408575057983},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.626213014125824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5613347887992859},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5296216607093811},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4929053783416748},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4615592360496521},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4501835107803345},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4333399534225464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43259376287460327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4268079996109009},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7472743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01350071v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01350071","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE ICASSP 2016, Mar 2016, Shangai, China. &#x27E8;10.1109/ICASSP.2016.7472743&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/4330","is_oa":false,"landing_page_url":"http://hdl.handle.net/10679/4330","pdf_url":null,"source":{"id":"https://openalex.org/S4306400232","display_name":"ECS Journal of Solid State Science and Technology (The Electrochemical Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802273670","host_organization_name":"Electrochemical Society","host_organization_lineage":["https://openalex.org/I2802273670"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01350071v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01350071","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE ICASSP 2016, Mar 2016, Shangai, China. &#x27E8;10.1109/ICASSP.2016.7472743&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1978633512","https://openalex.org/W1988732650","https://openalex.org/W1993741228","https://openalex.org/W1998726571","https://openalex.org/W1999497532","https://openalex.org/W2048715720","https://openalex.org/W2094732611","https://openalex.org/W2108881949","https://openalex.org/W2150769028","https://openalex.org/W2154339456","https://openalex.org/W2250641567","https://openalex.org/W2344822617","https://openalex.org/W2395750323","https://openalex.org/W2397479564","https://openalex.org/W2397634864","https://openalex.org/W2576939402","https://openalex.org/W4213403162","https://openalex.org/W6691613585","https://openalex.org/W6712325649","https://openalex.org/W6712532481","https://openalex.org/W6732407367"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5,23,76,112],"approach":[6,120],"for":[7,32,135],"minimizing":[8],"human":[9,67,133],"effort":[10,134],"in":[11,54,63],"manual":[12,73],"speaker":[13,97,104,115],"annotation.":[14,136],"Label":[15],"propagation":[16],"is":[17,42,81,106],"used":[18,82,94],"at":[19,108],"each":[20,87,109],"iteration":[21],"of":[22,89,101,132],"active":[24],"learning":[25],"cycle.":[26],"More":[27],"precisely,":[28],"a":[29,55,129],"selection":[30,46],"strategy":[31],"choosing":[33],"the":[34,52,72,90,102,125],"most":[35],"suitable":[36],"speech":[37],"track":[38],"to":[39,65,83,95],"be":[40],"labeled":[41],"proposed.":[43],"Four":[44],"different":[45],"strategies":[47],"are":[48,58,93],"evaluated":[49,107],"and":[50],"all":[51],"tracks":[53],"corresponding":[56],"cluster":[57],"gathered":[59],"using":[60,111],"agglomerative":[61],"clustering":[62],"order":[64],"propagate":[66],"annotations.":[68,85],"To":[69],"further":[70],"reduce":[71],"labor":[74],"required,":[75],"optical":[77],"character":[78],"recognition":[79],"system":[80],"bootstrap":[84],"At":[86],"step":[88,110],"cycle,":[91],"annotations":[92],"build":[96],"models.":[98],"The":[99,118],"quality":[100],"generated":[103],"models":[105],"i-vector":[113],"based":[114],"identification":[116],"system.":[117],"presented":[119],"shows":[121],"promising":[122],"results":[123],"on":[124],"REPERE":[126],"corpus":[127],"with":[128],"minimum":[130],"amount":[131]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
