{"id":"https://openalex.org/W67277430","doi":"https://doi.org/10.21437/interspeech.2011-58","title":"i-vector based speaker recognition on short utterances","display_name":"i-vector based speaker recognition on short utterances","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W67277430","doi":"https://doi.org/10.21437/interspeech.2011-58","mag":"67277430"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-58","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-58","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5023434638","display_name":"Ahilan Kanagasundaram","orcid":"https://orcid.org/0000-0002-0533-7986"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ahilan Kanagasundaram","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109211991","display_name":"Robbie Vogt","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Robbie Vogt","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077350001","display_name":"Michael Mason","orcid":"https://orcid.org/0000-0002-8494-9891"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Mason","raw_affiliation_strings":["Queensland University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":19.4128,"has_fulltext":false,"cited_by_count":239,"citation_normalized_percentile":{"value":0.99335654,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2341","last_page":"2344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976999759674072,"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":0.9603999853134155,"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/speech-recognition","display_name":"Speech recognition","score":0.7532726526260376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751820981502533},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7478494644165039},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7109711766242981},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6917951107025146},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6285663843154907},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6228711605072021},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5637335777282715},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5461907386779785},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5019841194152832},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4794144332408905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.437716007232666},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4352429211139679},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41550901532173157},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12236487865447998},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11907732486724854}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7532726526260376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751820981502533},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7478494644165039},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7109711766242981},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6917951107025146},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6285663843154907},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6228711605072021},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5637335777282715},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5461907386779785},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5019841194152832},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4794144332408905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.437716007232666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4352429211139679},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41550901532173157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12236487865447998},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11907732486724854},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2011-58","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-58","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.659.6501","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.659.6501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.qut.edu.au/46313/1/IS110023.PDF","raw_type":"text"},{"id":"pmh:oai:eprints.qut.edu.au:46313","is_oa":false,"landing_page_url":"http://wiki.ieeta.pt/wiki/index.php/InterSpeech_2011","pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 12th Annual Conference of the International Speech Communication Association","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W90661335","https://openalex.org/W111477576","https://openalex.org/W2136879537","https://openalex.org/W2170065313","https://openalex.org/W2183001115","https://openalex.org/W2403589179","https://openalex.org/W2406312423","https://openalex.org/W2407374891","https://openalex.org/W2612380871"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W1493012537","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Robust":[0],"speaker":[1,13],"verification":[2,89],"on":[3],"short":[4,124],"utterances":[5,92],"remains":[6],"a":[7,55,112],"key":[8],"consideration":[9],"when":[10,42],"deploying":[11],"automatic":[12],"recognition,":[14],"as":[15,94,96],"many":[16],"real":[17],"world":[18],"applications":[19],"often":[20],"have":[21],"access":[22],"to":[23,110],"only":[24],"limited":[25],"duration":[26],"speech":[27],"data.":[28],"This":[29],"paper":[30],"explores":[31],"how":[32],"the":[33,103,116],"recent":[34],"technologies":[35],"focused":[36],"around":[37],"total":[38],"variability":[39],"modeling":[40],"behave":[41],"training":[43],"and":[44,62,81],"testing":[45],"utterance":[46,125],"lengths":[47],"are":[48,51,108],"reduced.":[49],"Results":[50],"presented":[52,109],"which":[53],"provide":[54,111],"comparison":[56],"of":[57,99,115,120],"Joint":[58],"Factor":[59],"Analysis":[60,86],"(JFA)":[61],"i-vector":[63],"based":[64],"systems":[65],"including":[66],"various":[67],"compensation":[68],"techniques;":[69],"Within-Class":[70],"Covariance":[71],"Normalization":[72],"(WCCN),":[73],"LDA,":[74],"Scatter":[75],"Difference":[76],"Nuisance":[77],"Attribute":[78],"Projection":[79],"(SDNAP)":[80],"Gaussian":[82],"Probabilistic":[83],"Linear":[84],"Discriminant":[85],"(GPLDA).":[87],"Speaker":[88,105],"performance":[90,118],"for":[91],"with":[93],"little":[95],"2":[97],"sec":[98],"data":[100],"taken":[101],"from":[102],"NIST":[104],"Recognition":[106],"Evaluations":[107],"clearer":[113],"picture":[114],"current":[117],"characteristics":[119],"these":[121],"techniques":[122],"in":[123],"conditions.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
