{"id":"https://openalex.org/W2892142500","doi":"https://doi.org/10.1145/3242840.3242873","title":"Text Prompted Speaker Verification Based on Phoneme Clustering with Earth Mover's Distane and Cauchy-Schwarz Divergence","display_name":"Text Prompted Speaker Verification Based on Phoneme Clustering with Earth Mover's Distane and Cauchy-Schwarz Divergence","publication_year":2018,"publication_date":"2018-07-27","ids":{"openalex":"https://openalex.org/W2892142500","doi":"https://doi.org/10.1145/3242840.3242873","mag":"2892142500"},"language":"en","primary_location":{"id":"doi:10.1145/3242840.3242873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242840.3242873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Algorithms, Computing and Systems","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/A5006960202","display_name":"Zhuzi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuzi Chen","raw_affiliation_strings":["Tsinghua University, Tsinghua University, Haidian, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Tsinghua University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Tsinghua University, Tsinghua University, Haidian, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Tsinghua University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Tsinghua University, Tsinghua University, Haidian, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Tsinghua University, Haidian, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10286001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"88"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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":0.9854999780654907,"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/coarticulation","display_name":"Coarticulation","score":0.7047490477561951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6528278589248657},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6412231922149658},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6406599879264832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6222280263900757},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.534114420413971},{"id":"https://openalex.org/keywords/earth-movers-distance","display_name":"Earth mover's distance","score":0.5192515850067139},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.46765369176864624},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4634425938129425},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4478418231010437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667166233062744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32456836104393005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3219596743583679},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1311507523059845}],"concepts":[{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.7047490477561951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6528278589248657},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6412231922149658},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6406599879264832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6222280263900757},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.534114420413971},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.5192515850067139},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.46765369176864624},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4634425938129425},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4478418231010437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667166233062744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32456836104393005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3219596743583679},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1311507523059845},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3242840.3242873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242840.3242873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 2nd International Conference on Algorithms, Computing and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W78725893","https://openalex.org/W1556090664","https://openalex.org/W1996512145","https://openalex.org/W2041823554","https://openalex.org/W2125101937","https://openalex.org/W2132438428","https://openalex.org/W2136251587","https://openalex.org/W2144760012","https://openalex.org/W2150769028","https://openalex.org/W2164620631","https://openalex.org/W2169401222","https://openalex.org/W2186774823","https://openalex.org/W2295590090","https://openalex.org/W2295838856","https://openalex.org/W2398971481","https://openalex.org/W2510625446","https://openalex.org/W2514080268","https://openalex.org/W2746762848","https://openalex.org/W2962979137","https://openalex.org/W2963565199"],"related_works":["https://openalex.org/W2990278625","https://openalex.org/W1993499045","https://openalex.org/W1604595447","https://openalex.org/W4200613756","https://openalex.org/W2991639604","https://openalex.org/W4229448900","https://openalex.org/W2075046373","https://openalex.org/W83224372","https://openalex.org/W3151720380","https://openalex.org/W2139803903"],"abstract_inverted_index":{"For":[0],"short":[1,32,57],"duration":[2,58],"text":[3],"prompted":[4],"speaker":[5,17,26,34,60,80],"verification":[6,35],"where":[7],"the":[8,53,77,88,98,104,131],"amount":[9],"of":[10,31,52,87,103,113],"enrollment":[11,94],"data":[12,132],"is":[13,20,50],"limited":[14],"for":[15,56,65,76,164,177],"each":[16],"model,":[18],"it":[19],"hard":[21],"to":[22,81,116,129],"obtain":[23],"a":[24],"robust":[25],"representation.":[27],"In":[28,126],"these":[29],"situations":[30],"utterance":[33],"I-vector/GMM":[36],"approaches":[37],"work":[38],"even":[39],"worse":[40],"than":[41],"traditional":[42],"GMM-MAP":[43],"modeling":[44],"method.":[45],"GMM/HMM":[46],"framework":[47],"content":[48],"matching":[49],"one":[51],"state-of-the-art":[54],"paradigms":[55],"text-dependent":[59],"verification,":[61],"in":[62,93,97],"which":[63,114],"models":[64],"individual":[66],"lexical":[67,122,135],"such":[68],"as":[69,151,155],"words,":[70],"syllables,":[71],"or":[72],"phonemes":[73,89,105],"are":[74,120,142],"established":[75],"background":[78],"and":[79,101,109,123,137,148,169],"make":[82],"up":[83],"mismatch.":[84,125],"However,":[85],"some":[86],"do":[90],"not":[91],"occur":[92],"but":[95],"happen":[96],"testing":[99],"recordings,":[100],"most":[102],"have":[106],"different":[107],"preceding":[108],"succeeding":[110],"phonemes,":[111],"both":[112],"leads":[115],"coarticulation":[117],"difference.":[118],"These":[119],"called":[121],"context":[124,138],"this":[127],"work,":[128],"overcome":[130],"sparceness":[133],"caused":[134],"mismatch":[136],"mismatch,":[139],"phoneme":[140],"states":[141],"clustered":[143],"applying":[144],"Earth":[145,165],"Mover's":[146,166],"Distance":[147,167],"Cauchy-Schwarz":[149,178],"divergence":[150,179],"metrics.":[152],"Performance":[153],"improved":[154],"EER":[156,170],"lowered":[157,161,171],"by":[158,162,172],"6.2%,":[159],"minDCF08":[160,174],"1.9%":[163,176],"metric,":[168],"3.7%,":[173],"rised":[175],"metric.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}