{"id":"https://openalex.org/W142991516","doi":"https://doi.org/10.21437/interspeech.2012-579","title":"Diartk: an open source toolkit for research in multistream speaker diarization and its application to meetings recordings","display_name":"Diartk: an open source toolkit for research in multistream speaker diarization and its application to meetings recordings","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W142991516","doi":"https://doi.org/10.21437/interspeech.2012-579","mag":"142991516"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-579","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192695","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080162701","display_name":"Deepu Vijayasenan","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Deepu Vijayasenan","raw_affiliation_strings":["Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","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":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2170","last_page":"2173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9189308881759644},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8631057739257812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8181068897247314},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6716047525405884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5626038908958435},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4981060028076172},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.49779605865478516},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48195430636405945},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4580705165863037},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4420018196105957},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42176929116249084},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4199369251728058},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.416370153427124},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3709510564804077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3477778434753418},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09117540717124939}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9189308881759644},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8631057739257812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181068897247314},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6716047525405884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5626038908958435},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4981060028076172},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.49779605865478516},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48195430636405945},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4580705165863037},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4420018196105957},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42176929116249084},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4199369251728058},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.416370153427124},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3709510564804077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3477778434753418},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09117540717124939},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-579","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.4091","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.4091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2012/Vijayasenan_INTERSPEECH2012_2012.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192695","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192695","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:192695","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192695","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":[{"id":"https://metadata.un.org/sdg/17","score":0.44999998807907104,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1539780439","https://openalex.org/W1686946872","https://openalex.org/W1963976507","https://openalex.org/W1965279578","https://openalex.org/W1971791733","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2103723258","https://openalex.org/W2113386290","https://openalex.org/W2143038775","https://openalex.org/W2145303093","https://openalex.org/W2155386343","https://openalex.org/W2157667843","https://openalex.org/W2159591770","https://openalex.org/W2979454998"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"The":[0,110],"speaker":[1,50,77],"diarization":[2,78,88,142],"task":[3],"consists":[4],"of":[5,23,42,99,115],"inferring":[6],"\u201cwho":[7],"spoke":[8],"when":[9],"\u201d":[10],"in":[11,75],"an":[12,63,96,130],"audio":[13],"stream":[14],"without":[15],"any":[16],"prior":[17],"knowledge":[18],"and":[19,79,125,137],"has":[20,38],"been":[21,39],"object":[22],"several":[24,43],"NIST":[25,123],"international":[26],"evaluation":[27],"campaigns":[28],"is":[29,91,126],"last":[30],"years.":[31],"A":[32],"common":[33],"trend":[34],"for":[35],"improving":[36],"performances":[37],"the":[40,107],"use":[41,133],"different":[44,103],"feature":[45],"streams":[46],"as":[47,49],"diverse":[48],"location":[51],"features,":[52],"visual":[53],"features":[54,100],"or":[55],"noise":[56],"robust":[57],"acous-tic":[58],"features.":[59],"This":[60],"paper":[61],"describes":[62],"open":[64],"source":[65],"toolkit":[66],"re-leased":[67],"under":[68],"GPL":[69],"license":[70],"aiming":[71],"at":[72],"facilitating":[73],"research":[74],"mul-tistream":[76],"reproducing":[80],"state-of-the-art":[81],"re-sults.":[82],"In":[83],"contrary":[84],"to":[85,94,117,128,132,135],"other":[86],"related":[87],"toolkits,":[89],"it":[90],"ex-plicitly":[92],"designed":[93],"handle":[95],"arbitrary":[97],"number":[98],"with":[101],"very":[102],"statistics":[104],"while":[105],"limiting":[106],"computational":[108],"com-plexity.":[109],"release":[111],"includes":[112],"a":[113],"set":[114],"scripts":[116],"replicate":[118],"bench-mark":[119],"results":[120],"on":[121],"previous":[122],"evaluations":[124],"intended":[127],"provide":[129],"easy":[131],"software":[134],"study":[136],"include":[138],"novel":[139],"fea-tures":[140],"into":[141],"systems.":[143]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
