{"id":"https://openalex.org/W2098179789","doi":"https://doi.org/10.1109/icassp.2003.1202764","title":"Combining cross-stream and time dimensions in phonetic speaker recognition","display_name":"Combining cross-stream and time dimensions in phonetic speaker recognition","publication_year":2004,"publication_date":"2004-01-24","ids":{"openalex":"https://openalex.org/W2098179789","doi":"https://doi.org/10.1109/icassp.2003.1202764","mag":"2098179789"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202764","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Interactive Systems Laboratory, Taiwan","[Interactive Systems Laboratory, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratory, Taiwan","institution_ids":[]},{"raw_affiliation_string":"[Interactive Systems Laboratory, Taiwan]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039085741","display_name":"Ji\u0159\u00ed Navr\u00e1til","orcid":"https://orcid.org/0000-0001-6348-0812"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Navratil","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA","IBM Thomas J.Watson Research Center, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J.Watson Research Center, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111945151","display_name":"D.A. Reynolds","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.A. Reynolds","raw_affiliation_strings":["MIT Lincoln Laboratories, USA","MIT Lincoln Lab., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratories, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Lab., USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111958416","display_name":"Joseph P. Campbell","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.P. Campbell","raw_affiliation_strings":["MIT Lincoln Laboratories, USA","MIT Lincoln Lab., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratories, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Lab., USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023766935","display_name":"W.D. Andrews","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W.D. Andrews","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033390440","display_name":"Josh Abramson","orcid":"https://orcid.org/0009-0000-3496-6952"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J.S. Abramson","raw_affiliation_strings":["York University, Canada","York University - Canad\u00e1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"York University - Canad\u00e1","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6462,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.90759821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"IV","last_page":"800"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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/nist","display_name":"NIST","score":0.8395679593086243},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.7938932180404663},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.7287473678588867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7263576984405518},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7178464531898499},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6193023920059204},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5433877110481262},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4423593580722809},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43401896953582764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4017341136932373},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3528267443180084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34930944442749023},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10862118005752563},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09417033195495605}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8395679593086243},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.7938932180404663},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.7287473678588867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263576984405518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7178464531898499},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6193023920059204},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5433877110481262},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4423593580722809},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43401896953582764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4017341136932373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3528267443180084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34930944442749023},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10862118005752563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09417033195495605},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2003.1202764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202764","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.593","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.593","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/~qjin/Papers/icassp03-xstream.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.831.2011","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.831.2011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dtic.mil/get-tr-doc/pdf?AD%3DADA523753%26Location%3DU2%26doc%3DGetTRDoc.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.852.6983","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.852.6983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dtic.mil/dtic/tr/fulltext/u2/a523753.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W205402702","https://openalex.org/W1491198847","https://openalex.org/W1549285799","https://openalex.org/W1967477266","https://openalex.org/W2081240266","https://openalex.org/W2097427897","https://openalex.org/W2099345940","https://openalex.org/W2114851258","https://openalex.org/W2142730757","https://openalex.org/W2165880886","https://openalex.org/W3147810369","https://openalex.org/W6642173193"],"related_works":["https://openalex.org/W3173084154","https://openalex.org/W2982021180","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W2128567707","https://openalex.org/W2011383762","https://openalex.org/W2035962958","https://openalex.org/W2146546639","https://openalex.org/W4327499987","https://openalex.org/W2118039276"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"show":[2],"that":[3,67,78,111],"phonetic":[4],"sequences":[5],"from":[6,99],"multiple":[7,53],"languages":[8,54],"can":[9],"provide":[10],"effective":[11],"features":[12],"for":[13],"speaker":[14],"recognition.":[15],"So":[16],"far,":[17],"only":[18],"pronunciation":[19,48],"dynamics":[20,49],"in":[21,52,70,79],"the":[22,31,38,46,62,71,80,84,103,108,112],"time":[23,63,81],"dimension,":[24],"i.e.,":[25],"n-gram":[26],"modeling":[27,45,69],"on":[28,83],"each":[29],"of":[30,97],"phone":[32],"sequences,":[33],"have":[34],"been":[35],"examined.":[36],"In":[37],"JHU":[39],"2002":[40],"Summer":[41],"Workshop,":[42],"we":[43],"explored":[44],"statistical":[47],"across":[50],"streams":[51],"(cross-stream":[55],"dimension)":[56],"as":[57],"an":[58],"additional":[59],"component":[60],"to":[61],"dimension.":[64],"We":[65],"found":[66],"bigram":[68],"cross-stream":[72],"dimension":[73,82],"achieves":[74],"improved":[75],"performance":[76],"over":[77],"NIST":[85],"2001":[86],"Speaker":[87],"Recognition":[88],"Evaluation":[89],"Extended":[90],"Data":[91],"Task.":[92],"Moreover,":[93],"a":[94],"linear":[95],"combination":[96],"information":[98],"both":[100],"dimensions":[101,114],"at":[102],"score":[104],"level":[105],"further":[106],"improves":[107],"performance,":[109],"showing":[110],"two":[113],"contain":[115],"complementary":[116],"information.":[117]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
