{"id":"https://openalex.org/W7099311722","doi":null,"title":"INTERSPEECH 2010 A Hybrid Approach to Online Speaker Diarization","display_name":"INTERSPEECH 2010 A Hybrid Approach to Online Speaker Diarization","publication_year":2012,"publication_date":"2012-05-12","ids":{"openalex":"https://openalex.org/W7099311722"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.5523","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.5523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/hybridapproach10.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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","observed_orcids":["https://orcid.org/0000-0002-4110-7504"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Vaquero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283","observed_orcids":["https://orcid.org/0000-0001-7848-7283"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oriol Vinyals","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gerald Friedl","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerald Friedl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58136057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9854000210762024,"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":0.9854000210762024,"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":0.009600000455975533,"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/T12031","display_name":"Speech and dialogue systems","score":0.0032999999821186066,"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-identification","display_name":"speaker identification","score":0.746999979019165},{"id":"https://openalex.org/keywords/accuracy-latency-trade-off","display_name":"accuracy-latency trade-off","score":0.9470000267028809},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9128999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058000206947327},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.669700026512146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6381000280380249},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6033999919891357},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34769999980926514},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.225.5523","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.225.5523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/hybridapproach10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W164219236","https://openalex.org/W4399911883","https://openalex.org/W2896302892","https://openalex.org/W4400434625","https://openalex.org/W2534034218","https://openalex.org/W6940258093","https://openalex.org/W3200796884","https://openalex.org/W4283069218","https://openalex.org/W2807429203","https://openalex.org/W2917563231"],"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],"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],"SpeakerDiarization,online,incremental,hybrid":[103],"1.":[104]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}