{"id":"https://openalex.org/W2016443610","doi":"https://doi.org/10.1121/1.2028476","title":"Speaker normalization using neural networks","display_name":"Speaker normalization using neural networks","publication_year":1990,"publication_date":"1990-11-01","ids":{"openalex":"https://openalex.org/W2016443610","doi":"https://doi.org/10.1121/1.2028476","mag":"2016443610"},"language":"en","primary_location":{"id":"doi:10.1121/1.2028476","doi":"https://doi.org/10.1121/1.2028476","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.2028476","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/A5089183504","display_name":"Ashok Kumar Krishnamurthy","orcid":"https://orcid.org/0000-0002-3215-7622","observed_orcids":["https://orcid.org/0000-0002-3215-7622"]},"institutions":[{"id":"https://openalex.org/I2799950915","display_name":"Wright-Patterson Air Force Base","ror":"https://ror.org/0097e1k27","country_code":"US","type":"other","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2799950915","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok K. Krishnamurthy","raw_affiliation_strings":["Dept. of Elec. Eng., The Ohio State Univ., 2015 Nell Av., Columbus, OH 43210 H. G. Armstrong Aerospace Med. Res. Lab., AAMRL/BBA, Wright-Patterson Air Force Base, OH 45433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. Eng., The Ohio State Univ., 2015 Nell Av., Columbus, OH 43210 H. G. Armstrong Aerospace Med. Res. Lab., AAMRL/BBA, Wright-Patterson Air Force Base, OH 45433","institution_ids":["https://openalex.org/I2799950915","https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045191304","display_name":"Edward L. Riegelsberger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2799950915","display_name":"Wright-Patterson Air Force Base","ror":"https://ror.org/0097e1k27","country_code":"US","type":"other","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2799950915","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward L. Riegelsberger","raw_affiliation_strings":["Dept. of Elec. Eng., The Ohio State Univ., 2015 Nell Av., Columbus, OH 43210 H. G. Armstrong Aerospace Med. Res. Lab., AAMRL/BBA, Wright-Patterson Air Force Base, OH 45433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. Eng., The Ohio State Univ., 2015 Nell Av., Columbus, OH 43210 H. G. Armstrong Aerospace Med. Res. Lab., AAMRL/BBA, Wright-Patterson Air Force Base, OH 45433","institution_ids":["https://openalex.org/I2799950915","https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":null,"display_name":"Timothy R. Anderson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2799950915","display_name":"Wright-Patterson Air Force Base","ror":"https://ror.org/0097e1k27","country_code":"US","type":"other","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2799950915","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy R. Anderson","raw_affiliation_strings":["Dept. of Elec. Eng., The Ohio State Univ., 2015 Nell Av., Columbus, OH 43210 H. G. Armstrong Aerospace Med. Res. Lab., AAMRL/BBA, Wright-Patterson Air Force Base, OH 45433"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Elec. Eng., The Ohio State Univ., 2015 Nell Av., Columbus, OH 43210 H. G. Armstrong Aerospace Med. Res. Lab., AAMRL/BBA, Wright-Patterson Air Force Base, OH 45433","institution_ids":["https://openalex.org/I2799950915","https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"88","issue":"S1","first_page":"S103","last_page":"S103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0007999999797903001,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-normalization","display_name":"speaker normalization","score":0.9980000257492065},{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.5450000166893005},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.9229999780654907},{"id":"https://openalex.org/keywords/speaker-dependent-speech-recognition","display_name":"speaker-dependent recognition","score":0.8949999809265137},{"id":"https://openalex.org/keywords/vowel-recognition","display_name":"vowel recognition","score":0.9700000286102295},{"id":"https://openalex.org/keywords/timit-database","display_name":"TIMIT database","score":0.8610000014305115},{"id":"https://openalex.org/keywords/line-spectrum-frequencies","display_name":"line spectrum frequencies","score":0.8399999737739563},{"id":"https://openalex.org/keywords/auditory-model","display_name":"auditory model","score":0.8299999833106995}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.873088002204895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700573205947876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7243587374687195},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6301709413528442},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5953055620193481},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.57242751121521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5658671855926514},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5608681440353394},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5403963923454285},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5300226807594299},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5004100799560547},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4637129604816437},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45886608958244324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4468982517719269},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.42827755212783813},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36983057856559753},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2284506857395172},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/1.2028476","doi":"https://doi.org/10.1121/1.2028476","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.2028476","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1983239292","https://openalex.org/W2125082162","https://openalex.org/W1502707","https://openalex.org/W2016586411","https://openalex.org/W2163242682","https://openalex.org/W1499982184","https://openalex.org/W2055842011","https://openalex.org/W2108128176","https://openalex.org/W1996927508","https://openalex.org/W214728827"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,16,29,35,69,98,117],"method":[4],"of":[5,28,100,103,109,119,131],"speaker":[6,31,62,75,111],"normalization":[7,105,112],"using":[8,34,46],"neural":[9,40],"networks.":[10],"The":[11,42,55,77,89,107],"spectral":[12,20,26],"feature":[13,59],"vectors":[14,60],"from":[15,51,61,85],"speaker's":[17],"(speaker":[18,32],"A)":[19],"space":[21,27],"are":[22,64],"mapped":[23,58],"to":[24,68,81],"the":[25,52,86,101,104,110,129,132,141],"reference":[30],"R)":[33],"feedforward":[36],"multilayer":[37],"perceptron":[38],"(MLP)":[39],"network.":[41],"MLP":[43],"is":[44,80,94,114],"trained":[45,73],"phoentically":[47],"aligned":[48],"speech":[49,71],"data":[50],"two":[53],"speakers.":[54],"original":[56],"and":[57,128,134],"A":[63],"used":[65],"as":[66,97],"input":[67,120],"speaker-dependent":[70],"recognizer":[72],"for":[74,116],"R.":[76],"recognition":[78,92],"task":[79],"recognize":[82],"13":[83],"vowels":[84],"TIMIT":[87],"database.":[88],"improvement":[90],"in":[91],"accuracy":[93],"then":[95],"taken":[96],"measure":[99],"effectiveness":[102,108],"scheme.":[106],"technique":[113],"compared":[115],"number":[118],"representations:":[121],"line":[122],"spectrum":[123],"frequencies,":[124],"weighted":[125],"cepstral":[126],"coefficients,":[127],"outputs":[130],"Payton":[133],"Patterson-Holdsworth":[135],"auditory":[136],"models.":[137],"[Work":[138],"performed":[139],"under":[140],"AFOSR":[142],"Summer":[143],"Faculty":[144],"Research":[145],"Program.]":[146]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2016-06-24T00:00:00"}
