{"id":"https://openalex.org/W62995937","doi":"https://doi.org/10.21437/eurospeech.1997-119","title":"Speaker normalization through formant-based warping of the frequency scale","display_name":"Speaker normalization through formant-based warping of the frequency scale","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W62995937","doi":"https://doi.org/10.21437/eurospeech.1997-119","mag":"62995937"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-119","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},"type":"article","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/A5058682244","display_name":"Evandro Gouv\u00eaa","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evandro B. Gouvea","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard M. Stern","raw_affiliation_strings":["Department of Electrical and Computer Engineering School of Computer Science Carnegie Mellon University Pittsburgh, Pennsylvania 15213, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering School of Computer Science Carnegie Mellon University Pittsburgh, Pennsylvania 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058682244"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.2797,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.79647095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1139","last_page":"1142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/normalization","display_name":"Normalization (sociology)","score":0.9038988947868347},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8340940475463867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787352442741394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7616974115371704},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6939183473587036},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6394379734992981},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.6234068870544434},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4667741656303406},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4586096405982971},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4314340054988861},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.41645103693008423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39205288887023926}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9038988947868347},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8340940475463867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787352442741394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7616974115371704},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6939183473587036},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6394379734992981},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.6234068870544434},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4667741656303406},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4586096405982971},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4314340054988861},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.41645103693008423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39205288887023926},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1997-119","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.64.4935","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.4935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~robust/Papers/euro97-warp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2811237814","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3601516360","display_name":null,"funder_award_id":"Brazil","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G5079005330","display_name":null,"funder_award_id":"support","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G7295187585","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320332923","display_name":"U.S. Navy","ror":"https://ror.org/03ar0mv07"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1536719366","https://openalex.org/W2082381129","https://openalex.org/W2104663520","https://openalex.org/W2106119541","https://openalex.org/W2140567543","https://openalex.org/W2157590573","https://openalex.org/W2165871906","https://openalex.org/W3141839452","https://openalex.org/W4250530039"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W2090212048","https://openalex.org/W4393399007","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker-dependent":[0],"automatic":[1],"speech":[2,32],"recognition":[3,116],"systems":[4,10],"are":[5,15],"known":[6],"to":[7,17,37,53,100,146],"outperform":[8],"speaker-independent":[9],"when":[11],"enough":[12],"training":[13],"data":[14],"available":[16],"model":[18],"acoustical":[19],"variability":[20,39],"among":[21],"speakers.":[22,41],"Speaker":[23],"normalization":[24,45,91],"techniques":[25],"modify":[26],"the":[27,54,72,80,84,98,102,109,127],"spectral":[28],"representation":[29],"of":[30,67,83,86,104,111,131,134],"incoming":[31,73],"waveforms":[33],"in":[34,71,89],"an":[35],"attempt":[36],"reduce":[38,119],"between":[40],"Recent":[42],"successful":[43],"speaker":[44,90,123],"algorithms":[46,92],"have":[47],"incorporated":[48],"a":[49],"speaker-specific":[50],"frequency":[51,94],"warping":[52,138],"initial":[55],"signal":[56],"processing":[57],"stages.":[58],"These":[59],"algorithms,":[60],"however,":[61],"do":[62],"not":[63],"make":[64],"extensive":[65],"use":[66,85,103,110],"acoustic":[68,87],"features":[69,88],"contained":[70],"speech.":[74],"In":[75],"this":[76],"paper":[77],"we":[78,141],"study":[79,97],"possible":[81],"benefits":[82],"using":[93],"warping.":[95],"We":[96,125],"extent":[99],"which":[101],"such":[105],"features,":[106],"including":[107],"specifically":[108],"formant":[112],"frequencies,":[113],"can":[114],"improve":[115],"accuracy":[117],"and":[118,129,137],"computational":[120],"complexity":[121],"for":[122],"normalization.":[124],"examine":[126],"characteristics":[128],"limitations":[130],"several":[132],"types":[133],"feature":[135],"sets":[136],"functions":[139],"as":[140],"compare":[142],"their":[143],"performance":[144],"relative":[145],"existing":[147],"algorithms.":[148],"1.":[149]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}