{"id":"https://openalex.org/W20928449","doi":"https://doi.org/10.21437/interspeech.2004-520","title":"Real-time speaker identification","display_name":"Real-time speaker identification","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W20928449","doi":"https://doi.org/10.21437/interspeech.2004-520","mag":"20928449"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-520","doi":"https://doi.org/10.21437/interspeech.2004-520","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-520","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5102139802","display_name":"Pasi Frati","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasi Frati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078555338","display_name":"Evgeny A. Karpov","orcid":"https://orcid.org/0000-0001-7032-4375","observed_orcids":["https://orcid.org/0000-0001-7032-4375"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evgeny Karpov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322","observed_orcids":["https://orcid.org/0000-0002-4371-7322"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","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":1.662,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.8294687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1805","last_page":"1808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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":0.0,"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":0.8989999890327454},{"id":"https://openalex.org/keywords/real-time-identification","display_name":"real-time identification","score":0.7350000143051147},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.9940000176429749},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.9309999942779541},{"id":"https://openalex.org/keywords/computational-speed-up","display_name":"computational speed-up","score":0.6179999709129333},{"id":"https://openalex.org/keywords/feature-vector-matching","display_name":"feature vector matching","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.706030547618866},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6677162647247314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6117362976074219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6050657033920288},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5830442905426025},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5332920551300049},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5151535272598267},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5144286751747131},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5095870494842529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073689818382263},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.481020987033844},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46952930092811584},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44923004508018494},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4426416754722595},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4361618161201477},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.43254294991493225},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.42332321405410767},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4105411767959595},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3250854015350342},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2748802900314331},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-520","doi":"https://doi.org/10.21437/interspeech.2004-520","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-520","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W15100089","https://openalex.org/W42176576","https://openalex.org/W50589544","https://openalex.org/W60529718","https://openalex.org/W77513316","https://openalex.org/W88864901","https://openalex.org/W90591029","https://openalex.org/W142440765","https://openalex.org/W153948616","https://openalex.org/W181359039","https://openalex.org/W339880525","https://openalex.org/W1491751693","https://openalex.org/W1493163583","https://openalex.org/W1510046822","https://openalex.org/W1515135833","https://openalex.org/W1536811274","https://openalex.org/W1548442879","https://openalex.org/W1560013842","https://openalex.org/W1578856370","https://openalex.org/W1582747888","https://openalex.org/W1594273778","https://openalex.org/W1689977300","https://openalex.org/W1945356021","https://openalex.org/W1959596450","https://openalex.org/W1984784626","https://openalex.org/W1994529543","https://openalex.org/W1997873121","https://openalex.org/W2007266108","https://openalex.org/W2008957275","https://openalex.org/W2020532144","https://openalex.org/W2020883660","https://openalex.org/W2020888418","https://openalex.org/W2038044292","https://openalex.org/W2041823554","https://openalex.org/W2049644877","https://openalex.org/W2070176749","https://openalex.org/W2073671998","https://openalex.org/W2101047103","https://openalex.org/W2106710516","https://openalex.org/W2110652681","https://openalex.org/W2112180173","https://openalex.org/W2117321034","https://openalex.org/W2121178298","https://openalex.org/W2123158946","https://openalex.org/W2126782412","https://openalex.org/W2129244720","https://openalex.org/W2131618289","https://openalex.org/W2134383396","https://openalex.org/W2136631194","https://openalex.org/W2152402526","https://openalex.org/W2155798363","https://openalex.org/W2156331057","https://openalex.org/W2163874386","https://openalex.org/W2165880886","https://openalex.org/W2169159254","https://openalex.org/W2406898624","https://openalex.org/W2479250278","https://openalex.org/W2535438430","https://openalex.org/W2907162034"],"related_works":["https://openalex.org/W2099124598","https://openalex.org/W2188035560","https://openalex.org/W2604335382","https://openalex.org/W127011992","https://openalex.org/W1599802978","https://openalex.org/W1487516730","https://openalex.org/W2125163191","https://openalex.org/W2145450927"],"abstract_inverted_index":{"In":[0,50],"speaker":[1,20,43,61],"identification,":[2],"most":[3],"of":[4,17,34,41,48,67,81,111],"the":[5,14,18,22,25,32,39,42,46,65,72,79,89,126],"computation":[6],"originates":[7],"from":[8],"distance":[9],"or":[10],"likelihood":[11],"computations":[12],"between":[13],"feature":[15,35],"vectors":[16,69],"unknown":[19],"and":[21,45,78,116],"models":[23,44],"in":[24,125],"database.":[26],"The":[27,92],"identification":[28,90,127],"time":[29],"depends":[30],"on":[31,55],"number":[33,47,66,80],"vectors,":[36],"their":[37],"dimensionality,":[38],"complexity":[40],"speakers.":[49],"this":[51],"paper,":[52],"we":[53],"focus":[54],"optimizing":[56],"vector":[57],"quantization":[58],"(VQ)":[59],"based":[60,103],"identification.":[62],"We":[63,106],"reduce":[64],"test":[68,73],"by":[70,83],"pre-quantizing":[71],"sequence":[74],"prior":[75],"to":[76,98],"matching,":[77],"speakers":[82,87],"pruning":[84],"out":[85],"unlikely":[86],"during":[88],"process.":[91],"best":[93],"variants":[94],"are":[95],"then":[96],"generalized":[97],"Gaussian":[99],"mixture":[100],"model":[101],"(GMM)":[102],"modeling":[104],"also.":[105],"obtain":[107],"a":[108,122],"speed-up":[109],"factor":[110],"16:1":[112],"with":[113,118,121],"VQ-based":[114],"system,":[115],"34:1":[117],"GMM-based":[119],"system":[120],"minor":[123],"degradation":[124],"error":[128],"rate.":[129]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}