{"id":"https://openalex.org/W164219236","doi":"https://doi.org/10.21437/interspeech.2010-700","title":"A hybrid approach to online speaker diarization","display_name":"A hybrid approach to online speaker diarization","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W164219236","doi":"https://doi.org/10.21437/interspeech.2010-700","mag":"164219236"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-700","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5011739249","display_name":"Carlos Vaquero","orcid":"https://orcid.org/0000-0002-4110-7504"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carlos Vaquero","raw_affiliation_strings":["University of Zaragoza,"],"affiliations":[{"raw_affiliation_string":"University of Zaragoza,","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Vinyals","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011739249"],"corresponding_institution_ids":["https://openalex.org/I255234318"],"apc_list":null,"apc_paid":null,"fwci":0.9021,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78319199,"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":"2638","last_page":"2641"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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/T12031","display_name":"Speech and dialogue systems","score":0.9848999977111816,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9411661624908447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8164846897125244},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6946312785148621},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6065236926078796},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5856467485427856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5732818245887756},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5348958373069763},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4483557343482971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3558243215084076},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12215733528137207}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9411661624908447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164846897125244},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6946312785148621},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6065236926078796},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5856467485427856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5732818245887756},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5348958373069763},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4483557343482971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3558243215084076},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12215733528137207},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-700","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W9688279","https://openalex.org/W1587845029","https://openalex.org/W1771384906","https://openalex.org/W1991048564","https://openalex.org/W2041823554","https://openalex.org/W2144125830","https://openalex.org/W2149220986","https://openalex.org/W2166467513","https://openalex.org/W2338994564"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W184241528","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"This":[0],"article":[1,86],"presents":[2],"a":[3,14,19,66],"low-latency":[4,67],"speaker":[5,22,31,57,72],"diarization":[6,23,41,83],"system":[7,24,35],"(\u201cwho":[8,25],"is":[9,77],"speaking":[10],"now?\u201d)":[11],"based":[12],"on":[13,69],"hybrid":[15,108],"approach":[16,64],"that":[17,76],"combines":[18],"traditional":[20],"offline":[21,82],"spoke":[26],"when?\u201d)":[27],"with":[28,73],"an":[29,60,74],"online":[30],"identification":[32],"system.":[33,84],"The":[34,85],"fulfills":[36],"all":[37],"requirements":[38],"of":[39,93],"the":[40,52,63,70,80,88,91,94,98],"task,":[42],"i.e.":[43],"it":[44],"does":[45],"not":[46],"need":[47],"any":[48],"a-priori":[49],"information":[50],"about":[51],"input,":[53],"including":[54],"no":[55],"specific":[56],"models.":[58],"After":[59],"initialization":[61],"phase":[62],"allows":[65],"decision":[68],"current":[71],"accuracy":[75],"close":[78],"to":[79],"underlying":[81],"describes":[87],"approach,":[89],"evaluates":[90],"robustness":[92],"system,":[95],"and":[96],"analyzes":[97],"latency/accuracy":[99],"trade-off.":[100],"Index":[101],"Terms":[102],":S":[103],"peaker":[104],"Diarization,":[105],"online,":[106],"incremental,":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}