{"id":"https://openalex.org/W2081240266","doi":"https://doi.org/10.1109/icassp.2002.5743675","title":"Speaker identification using multilingual phone strings","display_name":"Speaker identification using multilingual phone strings","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2081240266","doi":"https://doi.org/10.1109/icassp.2002.5743675","mag":"2081240266"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743675","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5101665677","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0003-4163-6067"},"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":"Qin Jin","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, USA","[Interactive Systems Laboratories, Carnegie Mellon University, USA]"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Interactive Systems Laboratories, Carnegie Mellon University, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"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":"Tanja Schultz","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, USA","[Interactive Systems Laboratories, Carnegie Mellon University, USA]"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Interactive Systems Laboratories, Carnegie Mellon University, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","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":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, USA","[Interactive Systems Laboratories, Carnegie Mellon University, USA]"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Interactive Systems Laboratories, Carnegie Mellon University, USA]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101665677"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3869,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90165563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"145"},"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":0.9997000098228455,"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":0.9976000189781189,"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":0.7632416486740112},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7622616291046143},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.7451528906822205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6871112585067749},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6700181365013123},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6664842367172241},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6475984454154968},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5847804546356201},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5309550166130066},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49083882570266724},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4768874943256378},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.44540491700172424},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43700939416885376},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.43664056062698364},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42855870723724365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3835109770298004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3800390064716339},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1281203031539917},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06786388158798218},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06485855579376221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632416486740112},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7622616291046143},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7451528906822205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6871112585067749},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6700181365013123},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6664842367172241},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6475984454154968},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5847804546356201},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5309550166130066},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49083882570266724},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4768874943256378},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.44540491700172424},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43700939416885376},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.43664056062698364},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42855870723724365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3835109770298004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3800390064716339},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1281203031539917},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06786388158798218},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06485855579376221},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2002.5743675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743675","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000008530","is_oa":false,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000008530","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.2302","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.2302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/pub3/jin_qin_2002_1/jin_qin_2002_1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.5584","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.5584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~tanja/Papers/ICASSP02-qjin.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1491198847","https://openalex.org/W2008957275","https://openalex.org/W2033436836","https://openalex.org/W2098859361","https://openalex.org/W2129244720","https://openalex.org/W2165880886"],"related_works":["https://openalex.org/W2128073728","https://openalex.org/W4234190324","https://openalex.org/W1977167953","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W4396668120","https://openalex.org/W2126085626","https://openalex.org/W2129090883","https://openalex.org/W2972577568"],"abstract_inverted_index":{"Far-field":[0],"speaker":[1,54],"identification":[2,113],"is":[3,96],"very":[4],"challenging":[5],"since":[6],"varying":[7],"recording":[8],"conditions":[9,35,100],"often":[10],"result":[11],"in":[12,66],"un-matching":[13,42,99],"training":[14,32],"and":[15,33,101],"testing":[16,34],"situations.":[17],"Although":[18],"the":[19,56,91,104,110],"widely":[20],"used":[21],"Gaussian":[22],"Mixture":[23],"Models":[24],"(GMM)":[25],"approach":[26,51,95],"achieves":[27,115],"reasonable":[28],"good":[29],"results":[30,88],"when":[31],"match,":[36],"its":[37],"performance":[38,114],"degrades":[39],"dramatically":[40],"under":[41],"conditions.":[43],"In":[44],"this":[45],"paper":[46],"we":[47],"propose":[48],"a":[49,76],"new":[50],"for":[52],"far-field":[53],"identification:":[55],"usage":[57],"of":[58,78],"multilingual":[59],"phone":[60,64,93],"strings":[61],"derived":[62],"from":[63],"recognizers":[65],"eight":[67,83],"different":[68,84],"languages.":[69],"The":[70,87],"experiments":[71],"are":[72],"carried":[73],"out":[74],"on":[75,117],"database":[77],"30":[79],"speakers":[80],"recorded":[81],"with":[82],"microphone":[85],"distances.":[86],"show":[89],"that":[90],"multi-lingual":[92],"string":[94],"robust":[97],"against":[98],"significantly":[102],"outperforms":[103],"GMMs.":[105],"On":[106],"10-second":[107],"test":[108],"chunks,":[109],"average":[111],"closed-set":[112],"96.7%":[116],"variable":[118],"distance":[119],"data.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}