{"id":"https://openalex.org/W2938266773","doi":"https://doi.org/10.1109/icassp.2019.8683362","title":"Target and Non-target Speaker Discrimination by Humans and Machines","display_name":"Target and Non-target Speaker Discrimination by Humans and Machines","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938266773","doi":"https://doi.org/10.1109/icassp.2019.8683362","mag":"2938266773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100447410","display_name":"Soo\u2010Jin Park","orcid":"https://orcid.org/0000-0002-6350-6135"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soo Jin Park","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034455276","display_name":"Amber Afshan","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amber Afshan","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058020671","display_name":"Jody Kreiman","orcid":"https://orcid.org/0000-0002-5360-1729"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jody Kreiman","raw_affiliation_strings":["Depts. of Head and Neck Surgery and Linguistics, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Depts. of Head and Neck Surgery and Linguistics, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047895405","display_name":"Gary Yeung","orcid":"https://orcid.org/0000-0002-8325-1010"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Yeung","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112421995","display_name":"Abeer Alwan","orcid":"https://orcid.org/0000-0003-3390-9379"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abeer Alwan","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100447410"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77223071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6326","last_page":"6330"},"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":0.9994999766349792,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8569243550300598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.776658833026886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7538274526596069},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5939683318138123},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5729129314422607},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5570136308670044},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5325466990470886},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4808710217475891},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4780764579772949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4511028826236725},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44985732436180115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3826732337474823},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3022579550743103},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14831489324569702},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06431335210800171}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8569243550300598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.776658833026886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538274526596069},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5939683318138123},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5729129314422607},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5570136308670044},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5325466990470886},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4808710217475891},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4780764579772949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4511028826236725},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44985732436180115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3826732337474823},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3022579550743103},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14831489324569702},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06431335210800171},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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","id":"https://metadata.un.org/sdg/10","score":0.5},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W75992864","https://openalex.org/W97107628","https://openalex.org/W119864726","https://openalex.org/W1481604723","https://openalex.org/W1528905581","https://openalex.org/W1993854490","https://openalex.org/W2008833987","https://openalex.org/W2013374607","https://openalex.org/W2032988466","https://openalex.org/W2060729502","https://openalex.org/W2064364374","https://openalex.org/W2134501921","https://openalex.org/W2139896496","https://openalex.org/W2150769028","https://openalex.org/W2162219389","https://openalex.org/W2168561756","https://openalex.org/W2294192652","https://openalex.org/W2314642155","https://openalex.org/W2332809169","https://openalex.org/W2395619215","https://openalex.org/W2397464817","https://openalex.org/W2512149115","https://openalex.org/W2549754302","https://openalex.org/W2593474179","https://openalex.org/W2622879327","https://openalex.org/W2729622964","https://openalex.org/W2747262669","https://openalex.org/W2883691078","https://openalex.org/W3212485414","https://openalex.org/W4234095459","https://openalex.org/W4294940931","https://openalex.org/W6604007911","https://openalex.org/W6604892825","https://openalex.org/W6711976041","https://openalex.org/W6712445792","https://openalex.org/W6734675314","https://openalex.org/W6803627123"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W66821593","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W1521299571","https://openalex.org/W2185075503","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W4235705411"],"abstract_inverted_index":{"The":[0,163],"manner":[1],"in":[2,78],"which":[3],"acoustic":[4],"features":[5,64,106],"contribute":[6],"to":[7,16,96,117,182],"perceiving":[8],"speaker":[9,19,26,49,115,171],"identity":[10],"remains":[11],"unclear.":[12],"In":[13],"an":[14,145],"attempt":[15],"better":[17],"understand":[18],"perception,":[20],"we":[21],"investigated":[22],"human":[23,142,170,184],"and":[24,58,83,131,174],"machine":[25],"discrimination":[27,172],"with":[28,46,144,157],"utterances":[29],"shorter":[30],"than":[31],"2":[32],"seconds.":[33],"Sixty-five":[34],"listeners":[35],"performed":[36],"a":[37,68,113,166],"same":[38],"vs.":[39],"different":[40,105],"task.":[41],"Machine":[42,74],"performance":[43,75,149],"was":[44,76],"estimated":[45],"i-vector/PLDA-based":[47],"automatic":[48,177],"verification":[50],"systems,":[51],"one":[52],"using":[53,61],"mel-frequency":[54],"cepstral":[55],"coefficients":[56],"(MFCCs)":[57],"the":[59,81,132,158],"other":[60],"voice":[62,72],"quality":[63],"(VQual2)":[65],"inspired":[66],"by":[67],"psychoacoustic":[69],"model":[70],"of":[71,80],"quality.":[73],"measured":[77],"terms":[79],"detection":[82],"log-likelihood-ratio":[84],"cost":[85],"functions.":[86],"Humans":[87],"showed":[88],"higher":[89],"confidence":[90],"for":[91],"correct":[92,97],"target":[93],"decisions":[94,185],"compared":[95,116],"non-target":[98,123],"decisions,":[99],"suggesting":[100],"that":[101,176],"they":[102],"rely":[103],"on":[104],"and/or":[107],"decision":[108],"making":[109],"strategies":[110,173],"when":[111,118,136,187],"identifying":[112],"single":[114],"distinguishing":[119],"between":[120,129],"speakers.":[121],"For":[122],"trials,":[124],"responses":[125,143],"were":[126,138],"highly":[127],"correlated":[128],"humans":[130],"VQual2-based":[133,159],"system,":[134],"especially":[135,186],"speakers":[137,188],"perceptually":[139],"marked.":[140,190],"Fusing":[141],"MFCC-based":[146],"system":[147,160],"improved":[148],"over":[150],"human-only":[151],"or":[152],"MFCC-only":[153],"results,":[154],"while":[155],"fusing":[156],"did":[161],"not.":[162],"study":[164],"is":[165],"step":[167],"towards":[168],"understanding":[169],"suggests":[175],"systems":[178],"might":[179],"be":[180],"able":[181],"supplement":[183],"are":[189]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}