{"id":"https://openalex.org/W1564798076","doi":"https://doi.org/10.5075/epfl-thesis-1924","title":"Reconnaissance et transformation de locuteurs","display_name":"Reconnaissance et transformation de locuteurs","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W1564798076","doi":"https://doi.org/10.5075/epfl-thesis-1924","mag":"1564798076"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.tind.io:146026","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146026","pdf_url":"http://infoscience.epfl.ch/record/146026","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108355532","display_name":"Dominique Genoud","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Genoud, Dominique","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108355532"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9541000127792358,"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":0.9541000127792358,"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/speech-recognition","display_name":"Speech recognition","score":0.840888500213623},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7468453645706177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7013562321662903},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6114091277122498},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5532092452049255},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5420357584953308},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5231298804283142},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5072224140167236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3757670819759369},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3354690372943878},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17119455337524414}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.840888500213623},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7468453645706177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013562321662903},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6114091277122498},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5532092452049255},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5420357584953308},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5231298804283142},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5072224140167236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3757670819759369},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3354690372943878},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17119455337524414},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"pmh:oai:infoscience.tind.io:146026","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146026","pdf_url":"http://infoscience.epfl.ch/record/146026","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:32401","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/210415","pdf_url":"http://infoscience.epfl.ch/record/32401","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doctoral thesis"},{"id":"pmh:doi:10.5075/epfl-thesis-1924","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:doc.rero.ch:10894","is_oa":false,"landing_page_url":"http://library.epfl.ch/theses/?nr=1924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400148","display_name":"reroDoc Digital Library","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:infoscience.epfl.ch:32401","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/32401","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.5075/epfl-thesis-1924","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-1924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"},{"id":"mag:1564798076","is_oa":false,"landing_page_url":"https://infoscience.epfl.ch/record/32401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:146026","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146026","pdf_url":"http://infoscience.epfl.ch/record/146026","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1564798076.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2395673847","https://openalex.org/W2147286925","https://openalex.org/W2134510082","https://openalex.org/W2122098412","https://openalex.org/W2078953162","https://openalex.org/W2069976350","https://openalex.org/W1533303231"],"abstract_inverted_index":{"This":[0,226],"PhD":[1],"thesis":[2],"tries":[3],"to":[4,7,86,98,209,242,263,267,271,277,304,357,388,393,420,460,483,510,526],"understand":[5],"how":[6,525],"analyse,":[8],"decompose,":[9],"model":[10,123],"and":[11,39,61,85,118,127,132,351,368,416,433,517,556],"transform":[12],"the":[13,33,36,40,43,48,59,65,79,91,102,112,130,148,156,159,162,166,174,179,201,210,219,223,230,235,258,272,279,284,289,292,300,314,322,335,362,366,390,394,397,400,403,410,435,440,453,470,474,487,506,513,528,531,554,559],"vocal":[14],"identity":[15],"of":[16,35,42,50,78,82,90,105,129,158,165,173,181,200,203,212,228,316,321,325,334,341,353,399,409,452,464,558],"a":[17,76,83,106,171,182,198,204,213,297,332,339,422,450,462,467,479,539],"human":[18],"when":[19,493],"seen":[20],"through":[21],"an":[22,30,51,116,245,373,378,383,454,478],"automatic":[23,44,92,246],"speaker":[24,45,53,93,141,149,183,206,215,329,370,443,475,491,516,563],"recognition":[25,54,94,184,330,336,444,476,564],"application.":[26],"It":[27,143],"starts":[28],"with":[29,115],"introduction":[31],"explaining":[32],"properties":[34],"speech":[37,113,139,202,211,249],"signal":[38,114,164],"basis":[41],"recognition.":[46],"Then,":[47,170],"errors":[49,327],"operating":[52],"application":[55],"are":[56,101,109,138,191,310,413,428,496],"analysed.":[57],"From":[58],"deficiencies":[60],"mistakes":[62],"noticed":[63],"in":[64,155,178,193,328,402,418,562],"running":[66],"application,":[67,477],"some":[68,88],"observations":[69],"cm":[70],"be":[71,153,484,490],"made":[72],"which":[73,137],"will":[74],"imply":[75],"re-evaluation":[77],"characteristic":[80],"parameters":[81,104,220,231],"speaker,":[84,107],"reconsider":[87],"parts":[89,134],"chain.":[95],"In":[96,255,458],"order":[97,419,459],"determine":[99],"what":[100],"characterising":[103],"these":[108],"extracted":[110,221],"from":[111,161,222,240,291,365,377],"analysis":[117,126],"synthesis":[119],"harmonic":[120,131,280],"plus":[121],"noise":[122,133,285],"(H+N).":[124],"The":[125,189,407,426],"re-synthesis":[128],"indicate":[135],"those":[136],"or":[140,282,396],"dependent.":[142],"is":[144,186,232,252,276,344,349,386,437,504,535,548],"then":[145,414,536],"shown":[146],"that":[147,502],"discriminating":[150],"information":[151],"can":[152],"found":[154],"residual":[157],"subtraction":[160,298],"original":[163,293],"H+N":[167,224,290],"modeled":[168,287],"signal.":[169,294],"study":[172],"impostors":[175,190,309],"phenomenon,":[176],"essential":[177],"tuning":[180],"system,":[185],"carried":[187,253],"out.":[188,254],"simulated":[192],"two":[194],"ways:":[195],"first":[196],"by":[197,248,288,360],"transformation":[199],"source":[205],"(the":[207,216],"impostor)":[208],"target":[214],"client)":[217],"using":[218,530,545],"model.":[225],"way":[227,266],"transforming":[229],"efficient":[233],"as":[234,508],"false":[236,259,301],"acceptance":[237,260,302],"rate":[238,261,303],"grows":[239,262],"4%":[241],"23%.":[243],"Second,":[244],"imposture":[247],"sepent":[250],"concatenation":[251],"this":[256,503],"case":[257],"30%.":[264],"A":[265,346,521],"become":[268],"less":[269],"sensitive":[270],"spectral":[273],"modification":[274],"impostures":[275],"remove":[278],"part":[281,286],"even":[283,306],"Using":[295],"such":[296,382],"decreases":[299],"8%":[305],"if":[307,434],"transformed":[308],"used.":[311,497],"To":[312],"overcome":[313],"lack":[315],"training":[317],"data":[318,363],"\u2014":[319,331],"one":[320],"main":[323],"cause":[324],"modeling":[326,511,541],"decomposition":[333],"task":[337],"into":[338],"set":[340,461],"binary":[342,441],"classifiers":[343,412],"proposed.":[345,549],"classifier":[347],"matrix":[348],"built":[350],"each":[352],"its":[354],"elements":[355],"has":[356,482],"classify":[358],"word":[359,361],"coming":[364],"client":[367,401],"another":[369],"(named":[371],"here":[372],"anti-speaker,":[374],"randomly":[375],"chosen":[376],"extemal":[379],"database).":[380],"With":[381],"approach":[384,561],"it":[385],"possible":[387],"weight":[389],"results":[391,448],"according":[392],"vocabulary":[395],"neighbours":[398],"parameter":[404],"(acoustic)":[405],"space.":[406],"output":[408,424],"mamx":[411],"weighted":[415],"mixed":[417],"produce":[421],"single":[423],"score.":[425],"weights":[427],"estimated":[429],"on":[430,469],"validation":[431],"data,":[432],"weighting":[436],"done":[438],"properly,":[439],"pair":[442],"system":[445],"gives":[446],"better":[447],"than":[449],"state":[451],"HMM":[455],"based":[456],"system.":[457],"point":[463,468],"operation":[465],"(i.e.":[466],"COR":[471],"cuwe)":[472],"for":[473],"priori":[480],"threshold":[481,488,514,529],"determined.":[485],"Theoretically":[486],"should":[489],"independent":[492],"stochastic":[494],"models":[495],"However,":[498],"practical":[499,551],"experiments":[500,552],"show":[501,553],"not":[505],"case,":[507],"due":[509],"mismatch":[512],"becomes":[515],"utterance":[518],"length":[519],"dependant.":[520],"theoretical":[522],"framework":[523],"showing":[524],"adjust":[527],"local":[532],"likelihood":[533],"ratio":[534],"developed.":[537],"Finally,":[538],"last":[540],"error":[542],"correction":[543],"method":[544],"decision":[546],"fusion":[547,560],"Some":[550],"advantages":[555],"drawbacks":[557],"applications.":[565]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}