{"id":"https://openalex.org/W3094655774","doi":"https://doi.org/10.21437/interspeech.2020-1402","title":"Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions","display_name":"Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3094655774","doi":"https://doi.org/10.21437/interspeech.2020-1402","mag":"3094655774"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:openaire/1e9e1d5f-2613-4382-be81-8008f0567031","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/1e9e1d5f-2613-4382-be81-8008f0567031","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Prieto-Calero, S, Ortega, A, Espejo, I L & Lleida, E 2020, Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions. in Interspeech 2020. Proceedings of the International Conference on Spoken Language Processing, pp. 1511-1515, Interspeech 2020, Shanghai, China, 25/10/2020. https://doi.org/10.21437/Interspeech.2020-1402","raw_type":"info:eu-repo/semantics/publishedVersion"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/1e9e1d5f-2613-4382-be81-8008f0567031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057111078","display_name":"Santi Prieto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prieto-Calero, Santiago","raw_affiliation_strings":["VeriDas | das-Nano, Navarre, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VeriDas | das-Nano, Navarre, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903408","display_name":"Alfonso Ortega","orcid":"https://orcid.org/0000-0002-3886-7748"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ortega, Alfonso","raw_affiliation_strings":["ViVoLab, Arag\u00f3n Institute for Engineering Research (I3A) University of Zaragoza, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ViVoLab, Arag\u00f3n Institute for Engineering Research (I3A) University of Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048592470","display_name":"Iv\u00e1n L\u00f3pez\u2010Espejo","orcid":"https://orcid.org/0000-0001-8634-7897"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Espejo, Iv\u00e1n L\u00f3pez","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036493563","display_name":"Eduardo Lleida","orcid":"https://orcid.org/0000-0001-9137-4013"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Lleida, Eduardo","raw_affiliation_strings":["ViVoLab, Arag\u00f3n Institute for Engineering Research (I3A) University of Zaragoza, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ViVoLab, Arag\u00f3n Institute for Engineering Research (I3A) University of Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1354,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57126529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9930999875068665,"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/robustness","display_name":"Robustness (evolution)","score":0.7860540151596069},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7207918167114258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7131441235542297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7027193307876587},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.6189079284667969},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5571985840797424},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5430341362953186},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49683240056037903},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4620816707611084},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44483891129493713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3852768540382385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3830195665359497}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7860540151596069},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7207918167114258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7131441235542297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027193307876587},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.6189079284667969},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5571985840797424},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5430341362953186},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49683240056037903},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4620816707611084},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44483891129493713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3852768540382385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3830195665359497},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":2,"locations":[{"id":"pmh:oai:pure.atira.dk:openaire/1e9e1d5f-2613-4382-be81-8008f0567031","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/1e9e1d5f-2613-4382-be81-8008f0567031","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Prieto-Calero, S, Ortega, A, Espejo, I L & Lleida, E 2020, Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions. in Interspeech 2020. Proceedings of the International Conference on Spoken Language Processing, pp. 1511-1515, Interspeech 2020, Shanghai, China, 25/10/2020. https://doi.org/10.21437/Interspeech.2020-1402","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/1e9e1d5f-2613-4382-be81-8008f0567031","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85098122864&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"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":"Prieto-Calero , S , Ortega , A , Espejo , I L & Lleida , E 2020 , Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions . in Interspeech 2020 . Proceedings of the International Conference on Spoken Language Processing , pp. 1511-1515 , Interspeech 2020 , Shanghai , China , 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1402","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/1e9e1d5f-2613-4382-be81-8008f0567031","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/1e9e1d5f-2613-4382-be81-8008f0567031","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Prieto-Calero, S, Ortega, A, Espejo, I L & Lleida, E 2020, Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions. in Interspeech 2020. Proceedings of the International Conference on Spoken Language Processing, pp. 1511-1515, Interspeech 2020, Shanghai, China, 25/10/2020. https://doi.org/10.21437/Interspeech.2020-1402","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W177407077","https://openalex.org/W1279245896","https://openalex.org/W1524333225","https://openalex.org/W1581975840","https://openalex.org/W1625928172","https://openalex.org/W1665196592","https://openalex.org/W2022895291","https://openalex.org/W2075208738","https://openalex.org/W2099881084","https://openalex.org/W2187089797","https://openalex.org/W2640905660","https://openalex.org/W2726515241","https://openalex.org/W2802488037","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W3046457389"],"related_works":["https://openalex.org/W2018623685","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2316548414","https://openalex.org/W1992796048","https://openalex.org/W3141593045","https://openalex.org/W2182163200","https://openalex.org/W1516392727"],"abstract_inverted_index":{"The":[0,105],"performance":[1],"of":[2,45,49,68,102,117,132],"speaker":[3,29,91],"verification":[4,30],"systems":[5],"degrades":[6],"when":[7],"vocal":[8,133],"effort":[9,134],"conditions":[10,89],"between":[11,85],"enrollment":[12],"and":[13,56,87,110],"test":[14],"(e.g.,":[15],"shouted":[16,55,86,95,153],"vs.":[17],"normal":[18,57,88],"speech)":[19],"are":[20,63],"different.":[21],"This":[22],"is":[23,97,107,112],"a":[24,37,148],"potential":[25],"situation":[26],"in":[27,75,90,114,129],"non-cooperative":[28],"tasks.":[31],"In":[32],"this":[33,76],"paper,":[34],"we":[35,78],"present":[36],"study":[38],"on":[39],"different":[40],"methods":[41],"for":[42,70],"linear":[43],"compensation":[44,61],"embeddings":[46],"making":[47],"use":[48],"Gaussian":[50],"mixture":[51],"models":[52],"to":[53,81,138,147],"cluster":[54],"speech":[58,72,154],"domains.":[59],"These":[60],"techniques":[62],"borrowed":[64],"from":[65],"the":[66,83,115,126,130],"area":[67],"robustness":[69],"automatic":[71],"recognition":[73],"and,":[74],"work,":[77],"apply":[79],"them":[80],"compensate":[82],"mismatch":[84,135],"verification.":[92],"Before":[93],"compensation,":[94],"condition":[96],"automatically":[98],"detected":[99],"by":[100],"means":[101],"logistic":[103],"regression.":[104],"process":[106],"computationally":[108],"light":[109],"it":[111],"performed":[113],"back-end":[116],"an":[118],"x-vector":[119],"system.":[120],"Experimental":[121],"results":[122],"show":[123],"that":[124,150],"applying":[125],"proposed":[127],"approach":[128],"presence":[131],"yields":[136],"up":[137],"13.8%":[139],"equal":[140],"error":[141],"rate":[142],"relative":[143],"improvement":[144],"with":[145],"respect":[146],"system":[149],"applies":[151],"neither":[152],"detection":[155],"nor":[156],"compensation.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}