{"id":"https://openalex.org/W2798928049","doi":"https://doi.org/10.21437/odyssey.2018-50","title":"Supervector Compression Strategies to Speed up I-Vector System Development","display_name":"Supervector Compression Strategies to Speed up I-Vector System Development","publication_year":2018,"publication_date":"2018-06-06","ids":{"openalex":"https://openalex.org/W2798928049","doi":"https://doi.org/10.21437/odyssey.2018-50","mag":"2798928049"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2018-50","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-50","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.01156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031094144","display_name":"Ville Vestman","orcid":"https://orcid.org/0000-0002-7281-0278"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ville Vestman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031094144"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03969865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"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":0.9936000108718872,"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":0.972599983215332,"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/computer-science","display_name":"Computer science","score":0.7379853129386902},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6619275808334351},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5906556248664856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5682237148284912},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5402871966362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4990384578704834},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.4945313632488251},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4933454096317291},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4925442636013031},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4578631520271301},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4570297598838806},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.17253655195236206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16907161474227905},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13021114468574524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379853129386902},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6619275808334351},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5906556248664856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5682237148284912},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5402871966362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4990384578704834},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.4945313632488251},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4933454096317291},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4925442636013031},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4578631520271301},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4570297598838806},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.17253655195236206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16907161474227905},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13021114468574524},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/odyssey.2018-50","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2018-50","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2018)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.01156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.01156","pdf_url":"https://arxiv.org/pdf/1805.01156","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2798928049","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1805.01156.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1805.01156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.01156","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.01156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.01156","pdf_url":"https://arxiv.org/pdf/1805.01156","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5899999737739563,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2798928049.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2962767738","https://openalex.org/W3139985716","https://openalex.org/W67063673","https://openalex.org/W2058732030","https://openalex.org/W2610211568","https://openalex.org/W2127672898","https://openalex.org/W2943907267","https://openalex.org/W1839552948","https://openalex.org/W2293017759","https://openalex.org/W2187387698","https://openalex.org/W1902218045","https://openalex.org/W2393282889","https://openalex.org/W2389673752","https://openalex.org/W1980229494","https://openalex.org/W2006566011","https://openalex.org/W2011229062","https://openalex.org/W2006409748","https://openalex.org/W1999651846","https://openalex.org/W2545246288","https://openalex.org/W1554840114"],"abstract_inverted_index":{"The":[0,89,139,158],"front-end":[1],"factor":[2,65],"analysis":[3,10,66,102],"(FEFA),":[4],"an":[5],"extension":[6],"of":[7,115,145],"principal":[8],"component":[9],"(PPCA)":[11],"tailored":[12],"to":[13,26,45,50,84,169],"be":[14],"used":[15,93],"with":[16,97,156],"Gaussian":[17],"mixture":[18],"models":[19],"(GMMs),":[20],"is":[21],"currently":[22],"the":[23,46,76,112,121,148,179,186],"prevalent":[24],"approach":[25],"extract":[27],"compact":[28],"utterance-level":[29],"features":[30],"(i-vectors)":[31],"for":[32],"automatic":[33],"speaker":[34],"verification":[35],"(ASV)":[36],"systems.":[37],"Little":[38],"research":[39],"has":[40],"been":[41],"conducted":[42],"comparing":[43],"FEFA":[44],"conventional":[47],"PPCA":[48,73,187],"applied":[49],"maximum":[51],"a":[52,98,154],"posteriori":[53],"(MAP)":[54],"adapted":[55],"GMM":[56,87],"supervectors.":[57,88],"We":[58,105],"study":[59],"several":[60],"alternative":[61],"methods,":[62],"including":[63],"PPCA,":[64],"(FA),":[67],"and":[68,75,119,136,188],"two":[69,108],"supervised":[70,72,159],"approaches,":[71],"(SPPCA)":[74],"recently":[77],"proposed":[78],"probabilistic":[79,99],"partial":[80],"least":[81],"squares":[82],"(PPLS),":[83],"compress":[85],"MAP-adapted":[86],"resulting":[90],"i-vectors":[91],"are":[92,152],"in":[94,133,143,164,178],"ASV":[95,146],"tasks":[96],"linear":[100],"discriminant":[101],"(PLDA)":[103],"back-end.":[104],"experiment":[106],"on":[107,111,120,153],"different":[109],"datasets,":[110],"telephone":[113],"condition":[114],"NIST":[116],"SRE":[117],"2010":[118],"recent":[122],"VoxCeleb":[123],"corpus":[124],"collected":[125],"from":[126],"YouTube":[127],"videos":[128],"containing":[129],"celebrity":[130],"interviews":[131],"recorded":[132],"various":[134],"acoustical":[135],"technical":[137],"conditions.":[138],"results":[140],"suggest":[141],"that,":[142],"terms":[144],"accuracy,":[147],"supervector":[149,190],"compression":[150,191],"approaches":[151,160],"par":[155],"FEFA.":[157],"did":[161],"not":[162],"result":[163],"improved":[165],"performance.":[166],"In":[167],"comparison":[168],"FEFA,":[170],"we":[171],"obtained":[172],"more":[173],"than":[174],"hundred-fold":[175],"(100x)":[176],"speedups":[177],"total":[180],"variability":[181],"model":[182],"(TVM)":[183],"training":[184],"using":[185],"FA":[189],"approaches.":[192]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}