{"id":"https://openalex.org/W2075208738","doi":"https://doi.org/10.1109/icassp.2013.6639228","title":"Speaker identification from shouted speech: Analysis and compensation","display_name":"Speaker identification from shouted speech: Analysis and compensation","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2075208738","doi":"https://doi.org/10.1109/icassp.2013.6639228","mag":"2075208738"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2066/119425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076100840","display_name":"Cemal Hanil\u00e7i","orcid":"https://orcid.org/0000-0002-9174-0367"},"institutions":[{"id":"https://openalex.org/I131835042","display_name":"Bursa Uluda\u011f \u00dcni\u0307versi\u0307tesi\u0307","ror":"https://ror.org/03tg3eb07","country_code":"TR","type":"education","lineage":["https://openalex.org/I131835042"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cemal Hanilci","raw_affiliation_strings":["Bursa Uludag Universitesi, Bursa, TR","Dept. of Electron. Eng., Uludag Univ., Bursa, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bursa Uludag Universitesi, Bursa, TR","institution_ids":["https://openalex.org/I131835042"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Uludag Univ., Bursa, Turkey#TAB#","institution_ids":["https://openalex.org/I131835042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","Sch. of Comput., Univ. of Eastern Finland, Joensuu, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Eastern Finland, Joensuu, Finland#TAB#","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023224767","display_name":"Rahim Saeidi","orcid":"https://orcid.org/0000-0002-9084-0091"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Rahim Saeidi","raw_affiliation_strings":["Centre for Language and Speech Technology, Radboud University, Nijmegen, Netherlands","Centre for Language & Speech Technol., Radboud Univ. Nijmegen, Nijmegen, Netherlands#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language and Speech Technology, Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Centre for Language & Speech Technol., Radboud Univ. Nijmegen, Nijmegen, Netherlands#TAB#","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008322847","display_name":"Jouni Pohjalainen","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jouni Pohjalainen","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029946665","display_name":"Figen Erta\u015f","orcid":null},"institutions":[{"id":"https://openalex.org/I131835042","display_name":"Bursa Uluda\u011f \u00dcni\u0307versi\u0307tesi\u0307","ror":"https://ror.org/03tg3eb07","country_code":"TR","type":"education","lineage":["https://openalex.org/I131835042"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Figen Ertas","raw_affiliation_strings":["Department of Electronic Engineering, Uluda\u011f University, Bursa, Turkey","Dept. of Electron. Eng., Uludag Univ., Bursa, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Uluda\u011f University, Bursa, Turkey","institution_ids":["https://openalex.org/I131835042"]},{"raw_affiliation_string":"Dept. of Electron. Eng., Uludag Univ., Bursa, Turkey#TAB#","institution_ids":["https://openalex.org/I131835042"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4824,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86359769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8027","last_page":"8031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9692999720573425,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.860736608505249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.825007438659668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6901921629905701},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6551153659820557},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6389113664627075},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6057325005531311},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5189366340637207},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.5000338554382324},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4855356216430664},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4381740093231201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3770197629928589},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37612196803092957},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.325044184923172},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08441346883773804}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.860736608505249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.825007438659668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901921629905701},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6551153659820557},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6389113664627075},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6057325005531311},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5189366340637207},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.5000338554382324},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4855356216430664},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4381740093231201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3770197629928589},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37612196803092957},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.325044184923172},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08441346883773804},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2013.6639228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:ru:oai:repository.ubn.ru.nl:2066/119425","is_oa":true,"landing_page_url":"http://hdl.handle.net/2066/119425","pdf_url":"http://hdl.handle.net/2066/119425","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2013, 8027 - 8031. Vancouver, Canada : IEEE","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:d22ac718-d021-405c-a66e-cb388ae7318a","is_oa":false,"landing_page_url":"https://avesis.uludag.edu.tr/publication/details/d22ac718-d021-405c-a66e-cb388ae7318a/oai","pdf_url":null,"source":{"id":"https://openalex.org/S7407055210","display_name":"Bursa Uludag University - AVESIS","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.6091","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.6091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/shouted_speaker_ID.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:ru:oai:repository.ubn.ru.nl:2066/119425","is_oa":true,"landing_page_url":"http://hdl.handle.net/2066/119425","pdf_url":"http://hdl.handle.net/2066/119425","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2013, 8027 - 8031. Vancouver, Canada : IEEE","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2075208738.pdf","grobid_xml":"https://content.openalex.org/works/W2075208738.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W142801778","https://openalex.org/W175750906","https://openalex.org/W177407077","https://openalex.org/W204053250","https://openalex.org/W2049686551","https://openalex.org/W2078953162","https://openalex.org/W2089358776","https://openalex.org/W2096672501","https://openalex.org/W2100649345","https://openalex.org/W2123003832","https://openalex.org/W2141249992","https://openalex.org/W2156142001","https://openalex.org/W2165880886","https://openalex.org/W2234110698","https://openalex.org/W2397634864","https://openalex.org/W2399518911","https://openalex.org/W2917534502","https://openalex.org/W6605781699","https://openalex.org/W6607188615","https://openalex.org/W6608353291","https://openalex.org/W6712325649","https://openalex.org/W6712666484"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2048014685","https://openalex.org/W4385672897","https://openalex.org/W3009295899","https://openalex.org/W2129090883","https://openalex.org/W3204851989","https://openalex.org/W2972577568"],"abstract_inverted_index":{"Text-independent":[0],"speaker":[1,40,46],"identification":[2,47,114],"is":[3,86],"studied":[4],"using":[5],"neutral":[6],"and":[7,22,99],"shouted":[8],"speech":[9,92,100],"in":[10,66],"Finnish":[11],"to":[12,54,71,94,117],"analyze":[13],"the":[14,81,109,111,122],"effect":[15],"of":[16,62,108],"vocal":[17,58],"mode":[18,59,101],"mismatch":[19],"between":[20],"training":[21],"test":[23],"utterances.":[24],"Standard":[25],"mel-frequency":[26],"cepstral":[27],"coefficient":[28],"(MFCC)":[29],"features":[30],"with":[31],"Gaussian":[32],"mixture":[33],"model":[34],"(GMM)":[35],"recognizer":[36],"are":[37],"used":[38],"for":[39,79],"identification.":[41],"The":[42],"results":[43],"indicate":[44],"that":[45],"accuracy":[48,115],"reduces":[49],"from":[50],"perfect":[51],"(100":[52],"%)":[53],"8.71":[55,112],"%":[56,113,119],"under":[57],"mismatch.":[60],"Because":[61],"this":[63],"dramatic":[64],"degradation":[65],"recognition":[67],"accuracy,":[68],"we":[69],"propose":[70],"use":[72],"a":[73,89,96,106],"joint":[74],"density":[75],"GMM":[76],"mapping":[77,85],"technique":[78],"compensating":[80],"MFCC":[82],"features.":[83],"This":[84],"trained":[87],"on":[88],"disjoint":[90],"emotional":[91],"corpus":[93],"create":[95],"completely":[97],"speaker-":[98],"independent":[102],"emotion-neutralizing":[103],"mapping.":[104],"As":[105],"result":[107],"compensation,":[110],"increases":[116],"32.00":[118],"without":[120],"degrading":[121],"non-mismatched":[123],"train-test":[124],"conditions":[125],"much.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}