{"id":"https://openalex.org/W4301379562","doi":"https://doi.org/10.21437/icslp.1996-448","title":"Frame level likelihood normalization for text-independent speaker identification using Gaussian mixture models","display_name":"Frame level likelihood normalization for text-independent speaker identification using Gaussian mixture models","publication_year":1996,"publication_date":"1996-10-03","ids":{"openalex":"https://openalex.org/W4301379562","doi":"https://doi.org/10.21437/icslp.1996-448"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1996-448","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-448","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","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":"4th International Conference on Spoken Language Processing (ICSLP 1996)","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/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin P. Markov","raw_affiliation_strings":["Dept. of Information and Computer Sciences, Toyohashi Univ. of Tech., 1-1 Hibarigaoka, Tempaku-chou, Toyohashi-shi, Aichi-ken, 441 JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Information and Computer Sciences, Toyohashi Univ. of Tech., 1-1 Hibarigaoka, Tempaku-chou, Toyohashi-shi, Aichi-ken, 441 JAPAN","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018428974","display_name":"Seiichi Nakagawa","orcid":"https://orcid.org/0000-0002-6533-5536"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiichi Nakagawa","raw_affiliation_strings":["Dept. of Information and Computer Sciences, Toyohashi Univ. of Tech., 1-1 Hibarigaoka, Tempaku-chou, Toyohashi-shi, Aichi-ken, 441 JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Information and Computer Sciences, Toyohashi Univ. of Tech., 1-1 Hibarigaoka, Tempaku-chou, Toyohashi-shi, Aichi-ken, 441 JAPAN","institution_ids":["https://openalex.org/I136259955"]}]}],"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":3,"citation_normalized_percentile":{"value":0.5609493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1764","last_page":"1767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9900000095367432,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9739999771118164,"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/normalization","display_name":"Normalization (sociology)","score":0.8496979475021362},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6960700750350952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6880033016204834},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.605083703994751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5290899276733398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.528985857963562},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.49675828218460083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48443058133125305},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.4662313461303711},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4169030487537384},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36247342824935913},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22792264819145203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19921016693115234},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05701294541358948}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8496979475021362},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6960700750350952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880033016204834},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.605083703994751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5290899276733398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.528985857963562},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.49675828218460083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48443058133125305},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.4662313461303711},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4169030487537384},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36247342824935913},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22792264819145203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19921016693115234},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05701294541358948},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1996-448","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-448","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","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":"4th International Conference on Spoken Language Processing (ICSLP 1996)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2006712587","https://openalex.org/W2086082611","https://openalex.org/W2130039513","https://openalex.org/W2135346934","https://openalex.org/W3037213840"],"related_works":["https://openalex.org/W2370679465","https://openalex.org/W2128073728","https://openalex.org/W4234190324","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":{"In":[0],"this":[1,47],"paper":[2],"we":[3],"propose":[4],"a":[5],"new":[6,23],"speaker":[7,18],"identication":[8],"system,":[9,24],"where":[10],"the":[11,22,35,42,55,99],"likelihood":[12,70,93,102],"normalization":[13,94],"technique,":[14],"widely":[15],"used":[16],"for":[17,49],"verication,":[19],"is":[20,26,38,76,96],"introduced.In":[21],"which":[25],"based":[27],"on":[28],"Gaussian":[29],"Mixture":[30],"Models,":[31],"every":[32,65],"frame":[33,91],"of":[34,69],"test":[36],"utterance":[37],"inputed":[39],"to":[40,98],"all":[41,54],"reference":[43],"models":[44,56],"in":[45],"parallel.In":[46],"procedure,":[48],"each":[50],"frame,":[51],"likelihoods":[52],"from":[53],"are":[57],"available,":[58],"hence":[59],"they":[60],"can":[61],"be":[62],"normalized":[63],"at":[64],"frame.A":[66],"special":[67],"kind":[68],"normalization,":[71],"called":[72],"Weighting":[73],"Models":[74],"Rank,":[75],"also":[77],"proposed.Experiments":[78],"were":[79],"performed":[80],"using":[81],"two":[82],"databases":[83],"-TIMIT":[84],"and":[85],"NTT.Evaluation":[86],"results":[87],"clearly":[88],"show":[89],"that":[90],"level":[92],"technique":[95],"superior":[97],"standard":[100],"accumulated":[101],"approach.":[103]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}