{"id":"https://openalex.org/W2136199574","doi":"https://doi.org/10.1109/icassp.2012.6288992","title":"Keyword-conditioned phone N-gram modeling with contextual information for speaker verification","display_name":"Keyword-conditioned phone N-gram modeling with contextual information for speaker verification","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2136199574","doi":"https://doi.org/10.1109/icassp.2012.6288992","mag":"2136199574"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5106859201","display_name":"Kyu J. Han","orcid":null},"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":"Kyu J. Han","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029030495","display_name":"Jason Pelecanos","orcid":null},"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":"Jason Pelecanos","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113697338","display_name":"Mohamed Kamal Omar","orcid":null},"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":"Mohamed K. Omar","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19699107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"4797","last_page":"4800"},"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":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.9941999912261963,"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":0.8193928599357605},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7858746647834778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7341489195823669},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6800416707992554},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6198347210884094},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6138956546783447},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5100144147872925},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5009019374847412},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.4358949661254883},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4307933747768402},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4253844618797302},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4002669155597687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3643946945667267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09771037101745605},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07271277904510498},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06754684448242188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8193928599357605},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7858746647834778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7341489195823669},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6800416707992554},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6198347210884094},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6138956546783447},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5100144147872925},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5009019374847412},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.4358949661254883},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4307933747768402},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4253844618797302},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4002669155597687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643946945667267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09771037101745605},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07271277904510498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06754684448242188},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288992","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W205402702","https://openalex.org/W1488095445","https://openalex.org/W1595341470","https://openalex.org/W1631260214","https://openalex.org/W2016823731","https://openalex.org/W2086040361","https://openalex.org/W2097427897","https://openalex.org/W2100969003","https://openalex.org/W2153635508","https://openalex.org/W2153849757","https://openalex.org/W2160373860","https://openalex.org/W2165358012","https://openalex.org/W2401582030","https://openalex.org/W6608208890","https://openalex.org/W6629383007","https://openalex.org/W6635254389","https://openalex.org/W6636811518","https://openalex.org/W6682859417","https://openalex.org/W6712890763"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"our":[5,75,90],"current":[6],"work":[7],"on":[8,133],"automatic":[9],"speaker":[10,78,92,102],"recognition":[11],"using":[12],"keyword-conditioned":[13,76,100],"phone":[14,51],"N-gram":[15],"modeling.":[16],"We":[17],"propose":[18],"the":[19,108,113,120],"use":[20],"of":[21,97,119],"contextual":[22],"information":[23,60,69],"around":[24,43],"keywords":[25,44],"in":[26],"modeling":[27],"a":[28,33],"speaker's":[29],"pronunciation":[30,68],"characteristics":[31],"at":[32],"phonetic":[34,77,101],"level.":[35],"Our":[36],"approach":[37],"is":[38,71],"to":[39,73,105],"add":[40],"time":[41,63],"margins":[42,64],"when":[45],"aligning":[46],"keyword":[47],"regions":[48],"with":[49],"keyword-specific":[50],"events":[52],"for":[53,112,126],"feature":[54],"vector":[55],"generation.":[56],"Including":[57],"such":[58],"additional":[59],"by":[61],"incorporating":[62],"can":[65],"capture":[66],"idiosyncratic":[67],"and":[70,99],"shown":[72],"help":[74],"verification":[79,93,103],"system":[80,94],"achieve":[81,107],"more":[82],"than":[83],"50%":[84],"(relative)":[85],"performance":[86],"improvement.":[87],"This":[88],"leads":[89],"high-level":[91],"(i.e.,":[95],"fusion":[96],"non-conditioned":[98],"systems)":[104],"currently":[106],"best":[109],"published":[110],"result":[111],"English":[114],"8-conversation":[115],"enrollment":[116],"telephony":[117],"task":[118],"2008":[121],"NIST":[122],"Speaker":[123],"Recognition":[124],"Evaluation":[125],"systems":[127],"utilizing":[128],"features":[129],"not":[130],"based":[131],"directly":[132],"low-level":[134],"acoustic":[135],"information.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}