{"id":"https://openalex.org/W813769472","doi":"https://doi.org/10.21437/interspeech.2012-335","title":"Residual phase cepstrum coefficients with application to cross-lingual speaker verification","display_name":"Residual phase cepstrum coefficients with application to cross-lingual speaker verification","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W813769472","doi":"https://doi.org/10.21437/interspeech.2012-335","mag":"813769472"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-335","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101667153","display_name":"Jianglin Wang","orcid":"https://orcid.org/0000-0003-4243-9663"},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianglin Wang","raw_affiliation_strings":["Marquette University, Milwaukee, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Marquette University, Milwaukee, United States","institution_ids":["https://openalex.org/I102461120"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011384934","display_name":"Michael Johnson","orcid":"https://orcid.org/0009-0007-7352-4920"},"institutions":[{"id":"https://openalex.org/I102461120","display_name":"Marquette University","ror":"https://ror.org/04gr4te78","country_code":"US","type":"education","lineage":["https://openalex.org/I102461120"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Johnson","raw_affiliation_strings":["Marquette University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Marquette University","institution_ids":["https://openalex.org/I102461120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102461120"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1556","last_page":"1559"},"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":0.9979000091552734,"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":0.9526000022888184,"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/computer-science","display_name":"Computer science","score":0.7914402484893799},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7587260603904724},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7366763353347778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7065587043762207},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6498464345932007},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.621853768825531},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5814193487167358},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5813878178596497},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5696815252304077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4880737066268921},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4361540973186493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40169262886047363},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06728821992874146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914402484893799},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7587260603904724},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7366763353347778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7065587043762207},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6498464345932007},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.621853768825531},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5814193487167358},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5813878178596497},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5696815252304077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4880737066268921},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4361540973186493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40169262886047363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06728821992874146},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-335","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:epublications.marquette.edu:electric_fac-1071","is_oa":false,"landing_page_url":"https://epublications.marquette.edu/electric_fac/72","pdf_url":null,"source":{"id":"https://openalex.org/S4306401682","display_name":"e-Publications@Marquette (Marquette University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102461120","host_organization_name":"Marquette University","host_organization_lineage":["https://openalex.org/I102461120"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Faculty Research and Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.458.8638","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.458.8638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://speechlab.eece.mu.edu/johnson/papers/Wang_Interspeech2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W84241356","https://openalex.org/W279708261","https://openalex.org/W1520309894","https://openalex.org/W1969107787","https://openalex.org/W2041823554","https://openalex.org/W2053966553","https://openalex.org/W2103075368","https://openalex.org/W2115638247","https://openalex.org/W2129244720","https://openalex.org/W2141646521","https://openalex.org/W2153144850"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W66821593","https://openalex.org/W2051274299"],"abstract_inverted_index":{"Speaker":[0],"identification":[1,36],"and":[2,15,20,45,72,92,180],"verification":[3,89,132,187],"has":[4],"received":[5],"a":[6,107,129],"great":[7],"deal":[8],"of":[9,41,66,69,74,106,158,168,175],"attention":[10],"from":[11,122,135],"the":[12,26,32,47,67,75,80,104,136,156,169,173,176],"speech":[13],"community,":[14],"significant":[16,170],"gains":[17],"in":[18,52,64,84,172,186],"robustness":[19],"accuracy":[21],"have":[22,97],"been":[23],"obtained":[24],"over":[25,189],"past":[27],"decade":[28],"[1],":[29],"[2].":[30],"However,":[31],"features":[33,144,182],"used":[34],"for":[35,110,162],"are":[37,49,145],"still":[38],"primarily":[39,50],"representations":[40],"overall":[42,58],"spectral":[43],"characteristics,":[44],"thus":[46],"models":[48,76],"phonetic":[51,81,99],"nature,":[53],"differentiating":[54],"speakers":[55],"based":[56],"on":[57,128],"pronunciation":[59],"patterns.":[60,126],"This":[61,101],"creates":[62],"difficulties":[63],"terms":[65],"amount":[68,157],"enrollment":[70,91,159],"data":[71,94,160],"complexity":[73],"required":[77],"to":[78,118],"cover":[79],"space,":[82],"especially":[83],"tasks":[85],"such":[86],"as":[87],"cross-lingual":[88,130],"where":[90],"testing":[93],"may":[95],"not":[96],"similar":[98],"coverage.":[100],"paper":[102],"introduces":[103],"use":[105],"new":[108],"feature":[109],"speaker":[111,120,131,194],"verification,":[112,195],"residual":[113,199],"phase":[114,200],"cepstral":[115,152],"coefficients":[116,153],"(RPCC),":[117],"capture":[119],"characteristics":[121],"their":[123],"vocal":[124],"excitation":[125],"Results":[127],"task":[133],"taken":[134],"NIST":[137],"2004":[138],"SRE":[139],"demonstrate":[140],"that":[141],"these":[142],"RPCC":[143,181],"significantly":[146],"more":[147],"accurate":[148],"than":[149],"traditional":[150],"mel-frequency":[151],"(MFCC)":[154],"when":[155],"available":[161],"training":[163],"is":[164],"limited.":[165],"Additionally,":[166],"because":[167],"differences":[171],"nature":[174],"features,":[177],"combining":[178],"MFCC":[179],"shows":[183],"an":[184],"improvement":[185],"results":[188],"MFCCs":[190],"alone.":[191],"Index":[192],"Terms:":[193],"glottal":[196],"source":[197],"excitation,":[198],"cepstrum,":[201],"GMM,":[202],"UBM.":[203]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}