{"id":"https://openalex.org/W2964013807","doi":"https://doi.org/10.1109/icassp.2018.8462027","title":"Human and Machine Speaker Recognition Based on Short Trivial Events","display_name":"Human and Machine Speaker Recognition Based on Short Trivial Events","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2964013807","doi":"https://doi.org/10.1109/icassp.2018.8462027","mag":"2964013807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5100376495","display_name":"Miao Zhang","orcid":"https://orcid.org/0000-0003-3582-6075"},"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":true,"raw_author_name":"Miao Zhang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075264909","display_name":"Xiaofei Kang","orcid":"https://orcid.org/0000-0002-1733-079X"},"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":"Xiaofei Kang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006041868","display_name":"Yanqing Wang","orcid":"https://orcid.org/0000-0002-5961-0482"},"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":"Yanqing Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"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":"Lantian Li","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"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":"Zhiyuan Tang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049083571","display_name":"Haisheng Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I72427458","display_name":"JDSU (United States)","ror":"https://ror.org/01a5v8x09","country_code":"US","type":"company","lineage":["https://openalex.org/I72427458"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haisheng Dai","raw_affiliation_strings":["JD AI Research"],"affiliations":[{"raw_affiliation_string":"JD AI Research","institution_ids":["https://openalex.org/I72427458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"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":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100376495"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.59568738,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7492077,"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":"5009","last_page":"5013"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9901999831199646,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8542264103889465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8102816343307495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7513418197631836},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6437377333641052},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6204316020011902},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6083282232284546},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5174439549446106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43069303035736084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3874189257621765},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1143866777420044}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8542264103889465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8102816343307495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513418197631836},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6437377333641052},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6204316020011902},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6083282232284546},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5174439549446106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43069303035736084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3874189257621765},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1143866777420044},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W102958777","https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1936725236","https://openalex.org/W1988575427","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2075208738","https://openalex.org/W2106790438","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2316482457","https://openalex.org/W2398313355","https://openalex.org/W2610124020","https://openalex.org/W2962832278","https://openalex.org/W2964269671","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2053269318","https://openalex.org/W2157423375","https://openalex.org/W3148366653"],"abstract_inverted_index":{"Human":[0],"speech":[1,88],"often":[2],"has":[3],"events":[4,22,48],"that":[5,90],"we":[6,83],"will":[7],"call":[8],"trivial":[9,21,47,86,132],"events,":[10,98,133,160],"e.g.,":[11],"cough,":[12],"laugh":[13],"and":[14,26,35,94,99,112,129],"sniff.":[15],"Compared":[16],"to":[17,65,72,127,135,144],"regular":[18],"speech,":[19],"these":[20,46,154],"are":[23,37,49,62],"usually":[24],"short":[25,149],"variable,":[27],"thus":[28],"generally":[29],"regarded":[30],"as":[31,57,60],"not":[32],"speaker":[33,42,76,102,164],"discriminative":[34],"so":[36,68],"largely":[38],"ignored":[39],"by":[40,108,122],"present":[41],"recognition":[43,103],"research.":[44],"However,":[45],"highly":[50],"valuable":[51],"in":[52],"some":[53],"particular":[54],"circumstances":[55],"such":[56],"forensic":[58],"examination,":[59],"they":[61],"less":[63],"subjected":[64],"intentional":[66],"change,":[67],"can":[69],"be":[70],"used":[71],"discover":[73],"the":[74,115,131,147],"genuine":[75],"from":[77,142],"disguised":[78],"speech.":[79],"In":[80],"this":[81,106],"paper,":[82],"collect":[84],"a":[85],"event":[87],"database":[89],"involves":[91],"75":[92],"speakers":[93],"6":[95],"types":[96,158],"of":[97,153,159],"report":[100],"preliminary":[101],"results":[104],"on":[105],"database,":[107],"both":[109],"human":[110],"listeners":[111],"machines.":[113],"Particularly,":[114],"deep":[116],"feature":[117],"learning":[118],"technique":[119],"recently":[120],"proposed":[121],"our":[123],"group":[124],"is":[125],"utilized":[126],"analyze":[128],"recognize":[130],"leading":[134],"acceptable":[136],"equal":[137],"error":[138],"rates":[139],"(EERs)":[140],"ranging":[141],"5%":[143],"15%":[145],"despite":[146],"extremely":[148],"durations":[150],"(0.2-0.5":[151],"seconds)":[152],"events.":[155],"Comparing":[156],"different":[157],"`hmm'":[161],"seems":[162],"more":[163],"discriminative.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}