{"id":"https://openalex.org/W2894952638","doi":"https://doi.org/10.23919/biosig.2018.8553619","title":"Enhanced low-latency speaker spotting using selective cluster enrichment","display_name":"Enhanced low-latency speaker spotting using selective cluster enrichment","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2894952638","doi":"https://doi.org/10.23919/biosig.2018.8553619","mag":"2894952638"},"language":"en","primary_location":{"id":"doi:10.23919/biosig.2018.8553619","is_oa":false,"landing_page_url":"https://doi.org/10.23919/biosig.2018.8553619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference of the Biometrics Special Interest Group (BIOSIG)","raw_type":"proceedings-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/A5046246613","display_name":"Jos\u00e9 Patino","orcid":"https://orcid.org/0000-0001-7193-0721"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Jose Patino","raw_affiliation_strings":["Department of Digital Security, EURECOM, Sophia Antipolis, France"],"affiliations":[{"raw_affiliation_string":"Department of Digital Security, EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078464030","display_name":"H\u00e9ctor Delgado","orcid":"https://orcid.org/0000-0002-4475-2517"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hector Delgado","raw_affiliation_strings":["Department of Digital Security, EURECOM, Sophia Antipolis, France"],"affiliations":[{"raw_affiliation_string":"Department of Digital Security, EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["Department of Digital Security, EURECOM, Sophia Antipolis, France"],"affiliations":[{"raw_affiliation_string":"Department of Digital Security, EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046246613"],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10685484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.842052698135376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628742456436157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7225082516670227},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6066046953201294},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5483255982398987},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.515263557434082},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5088756084442139},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.47788894176483154},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4416120946407318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2732797861099243},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12983158230781555},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12265169620513916}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.842052698135376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628742456436157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7225082516670227},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6066046953201294},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5483255982398987},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.515263557434082},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5088756084442139},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.47788894176483154},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4416120946407318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2732797861099243},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12983158230781555},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12265169620513916}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/biosig.2018.8553619","is_oa":false,"landing_page_url":"https://doi.org/10.23919/biosig.2018.8553619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference of the Biometrics Special Interest Group (BIOSIG)","raw_type":"proceedings-article"},{"id":"pmh:oai:fr.eurecom:5702","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/5702","pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BIOSIG 2018, 17th International Conference of the Biometrics Special Interest Group, 26-29 September 2018, Darmstadt, Germany\\t","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W82466267","https://openalex.org/W1502693945","https://openalex.org/W1965819578","https://openalex.org/W2038162002","https://openalex.org/W2041823554","https://openalex.org/W2081074144","https://openalex.org/W2083751884","https://openalex.org/W2107638917","https://openalex.org/W2130708324","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2404617565","https://openalex.org/W2405137844","https://openalex.org/W2405768527","https://openalex.org/W2746241180","https://openalex.org/W2746574320","https://openalex.org/W2807429203","https://openalex.org/W6603310176"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Low-latency":[0],"speaker":[1,29,32],"spotting":[2],"(LLSS)":[3],"calls":[4],"for":[5,141],"the":[6,20,45,54,65,71,74,92],"rapid":[7],"detection":[8,33],"of":[9,48,73],"known":[10],"speakers":[11,123],"within":[12,34,99],"multi-speaker":[13,101,138],"audio":[14,102,139],"streams.":[15],"While":[16],"previous":[17],"work":[18],"showed":[19],"potential":[21],"to":[22,41,64,70,90,95],"develop":[23],"efficient":[24],"LLSS":[25,80,114],"solutions":[26],"by":[27],"combining":[28],"diarization":[30,61,75,93],"and":[31,58,104],"an":[35],"online":[36],"processing":[37],"framework,":[38],"it":[39],"failed":[40],"move":[42],"significantly":[43],"beyond":[44],"traditional":[46],"definition":[47],"diarization.":[49],"This":[50],"paper":[51,119],"shows":[52,120],"that":[53,59,121],"latter":[55],"needs":[56],"rethinking":[57],"a":[60,100,109,128],"sub-system":[62],"tailored":[63],"end":[66],"application,":[67],"rather":[68],"than":[69],"minimisation":[72],"error":[76,131],"rate,":[77],"can":[78,124],"improve":[79],"performance.":[81],"The":[82,113],"proposed":[83],"selective":[84],"cluster":[85],"enrichment":[86],"algorithm":[87],"is":[88],"used":[89],"guide":[91],"system":[94],"better":[96],"model":[97],"segments":[98],"stream":[103],"hence":[105],"detect":[106],"more":[107],"reliably":[108],"given":[110],"target":[111,122],"speaker.":[112],"solution":[115],"reported":[116],"in":[117,137],"this":[118],"be":[125],"detected":[126],"with":[127],"16%":[129],"equal":[130],"rate":[132],"after":[133],"having":[134],"been":[135],"active":[136],"streams":[140],"only":[142],"15":[143],"seconds.":[144]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}