{"id":"https://openalex.org/W2807429203","doi":"https://doi.org/10.21437/odyssey.2018-20","title":"Low-latency speaker spotting with online diarization and detection","display_name":"Low-latency speaker spotting with online diarization and detection","publication_year":2018,"publication_date":"2018-06-06","ids":{"openalex":"https://openalex.org/W2807429203","doi":"https://doi.org/10.21437/odyssey.2018-20","mag":"2807429203"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2018-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/276346","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046246613","display_name":"Jos\u00e9 Patino","orcid":"https://orcid.org/0000-0001-7193-0721"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jose Patino","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090981476","display_name":"Ruiqing Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ruiqing Yin","raw_affiliation_strings":["Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078464030","display_name":"H\u00e9ctor Delgado","orcid":"https://orcid.org/0000-0002-4475-2517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Delgado","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bredin","raw_affiliation_strings":["Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030911108","display_name":"Ali Komaty","orcid":"https://orcid.org/0000-0002-7329-587X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alain Komaty","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013670630","display_name":"Guillaume Wisniewski","orcid":"https://orcid.org/0000-0002-4445-080X"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Wisniewski","raw_affiliation_strings":["Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112867496","display_name":"Claude Barras","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claude Barras","raw_affiliation_strings":["Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur"],"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","institution_ids":["https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016330764","display_name":"S\u00e9bastien Marcel","orcid":"https://orcid.org/0000-0002-2497-9140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Marcel","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5046246613"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.38993721,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83525918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"146"},"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":0.9990000128746033,"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":0.9914000034332275,"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":0.8949841260910034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8192247152328491},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.677635908126831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5845426321029663},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4700036644935608},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4495502710342407},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4367576539516449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3649265170097351},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10729661583900452}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8949841260910034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192247152328491},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.677635908126831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5845426321029663},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4700036644935608},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4495502710342407},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4367576539516449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3649265170097351},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10729661583900452}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/odyssey.2018-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01836490v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01836490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Odyssey 2018: The Speaker and Language Recognition Workshop, ISCA, Jun 2018, Les Sables d'Olonne, France. &#x27E8;10.21437/Odyssey.2018-20&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:infoscience.epfl.ch:276346","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/276346","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/276346","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:276346","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/276346","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/276346","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W1965819578","https://openalex.org/W1968491588","https://openalex.org/W1995268755","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2083751884","https://openalex.org/W2107638917","https://openalex.org/W2107807822","https://openalex.org/W2130708324","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2164031777","https://openalex.org/W2295590090","https://openalex.org/W2399518911","https://openalex.org/W2402704384","https://openalex.org/W2405137844","https://openalex.org/W2516631658","https://openalex.org/W2746574320","https://openalex.org/W2746871870","https://openalex.org/W2749006664","https://openalex.org/W2750259098","https://openalex.org/W2963702081"],"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":{"This":[0],"paper":[1,34],"introduces":[2],"a":[3,50,94,157,160,176,190],"new":[4,51],"task":[5,18],"termed":[6],"low-latency":[7],"speaker":[8,42,46,88,116],"spotting":[9],"(LLSS).":[10],"Related":[11],"to":[12,37,55,71,122,127,156,162,178],"security":[13],"and":[14,44,48,53,87,98,169,203],"intelligence":[15],"applications,":[16],"the":[17,20,38,73,81,164,171],"involves":[19],"detection,":[21,170],"as":[22,24],"soon":[23],"possible,":[25],"of":[26,41,58,75,133,166],"known":[27],"speakers":[28],"within":[29],"multi-speaker":[30],"audio":[31],"streams.":[32],"The":[33,130],"describes":[35],"differences":[36],"established":[39],"fields":[40],"diarization":[43,86,101,168],"automatic":[45],"verification":[47],"proposes":[49],"protocol":[52],"metrics":[54],"support":[56],"exploration":[57],"LLSS.":[59],"These":[60],"can":[61,195],"be":[62,154,196],"used":[63],"together":[64],"with":[65],"an":[66],"existing,":[67],"publicly":[68,200],"available":[69,201],"database":[70],"assess":[72],"performance":[74,132],"LLSS":[76,173],"solutions":[77,146],"also":[78],"proposed":[79,172],"in":[80,125,182],"paper.":[82],"They":[83],"combine":[84],"online":[85,100,167],"detection":[89,106,128],"systems.":[90],"Diarization":[91],"systems":[92],"include":[93],"naive,":[95],"over-segmentation":[96],"approach":[97],"fully-fledged":[99],"using":[102,109,199],"segmental":[103],"i-vectors.":[104],"Speaker":[105],"is":[107,136,143],"performed":[108],"Gaussian":[110],"mixture":[111],"models,":[112],"i-vectors":[113],"or":[114],"neural":[115],"embeddings.":[117],"Metrics":[118],"reflect":[119],"different":[120],"approaches":[121],"characterise":[123],"latency":[124,142,152],"addition":[126],"performance.":[129],"relative":[131],"each":[134],"solution":[135],"dependent":[137],"on":[138],"latency.":[139],"When":[140],"higher":[141],"admissible,":[144],"i-vector":[145],"perform":[147],"well;":[148],"embeddings":[149],"excel":[150],"when":[151],"must":[153],"kept":[155],"minimum.":[158],"With":[159],"need":[161],"improve":[163],"reliability":[165],"framework":[174],"provides":[175],"vehicle":[177],"fuel":[179],"future":[180],"research":[181,192],"both":[183],"areas.":[184],"In":[185],"this":[186],"respect,":[187],"we":[188],"embrace":[189],"reproducible":[191],"policy;":[193],"results":[194],"readily":[197],"reproduced":[198],"resources":[202],"open":[204],"source":[205],"codes.":[206]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
