{"id":"https://openalex.org/W1991256687","doi":"https://doi.org/10.1109/icassp.2002.5745590","title":"Signal Bias Removal based GMM for robust speaker recognition","display_name":"Signal Bias Removal based GMM for robust speaker recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1991256687","doi":"https://doi.org/10.1109/icassp.2002.5745590","mag":"1991256687"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745590","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/A5100461241","display_name":"Yujin Kim","orcid":"https://orcid.org/0000-0003-4261-1793"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yu-Jin Kim","raw_affiliation_strings":["INHA University, Republic of Korea","Inha Univ. (Republic of Korea)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INHA University, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]},{"raw_affiliation_string":"Inha Univ. (Republic of Korea)","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113877644","display_name":"Jae-Ho Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Ho Chung","raw_affiliation_strings":["INHA University, Republic of Korea","Inha Univ. (Republic of Korea)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INHA University, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]},{"raw_affiliation_string":"Inha Univ. (Republic of Korea)","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191879574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08461538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"IV","last_page":"4163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9505000114440918,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robustness","display_name":"Robustness (evolution)","score":0.808882474899292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7106349468231201},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6982675790786743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6823393702507019},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6447545289993286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6098278164863586},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.49235546588897705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4707494378089905},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43379008769989014},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4231584072113037},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2934226989746094}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.808882474899292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7106349468231201},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6982675790786743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823393702507019},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6447545289993286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6098278164863586},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.49235546588897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4707494378089905},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43379008769989014},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4231584072113037},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2934226989746094},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5745590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745590","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2128073728","https://openalex.org/W4234190324","https://openalex.org/W1197719229","https://openalex.org/W2092874659","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2052112670","https://openalex.org/W4396668120","https://openalex.org/W2129090883","https://openalex.org/W2972577568"],"abstract_inverted_index":{"In":[0,87],"this":[1],"paper,":[2],"we":[3,90,121],"focus":[4],"on":[5,58,104,116],"the":[6,52,55,63,66,71,74,78,92,100,111,126,132],"combined":[7],"method":[8,25,102],"of":[9,20,30,54,65,73,114],"SBR":[10],"and":[11,13,18,70,82,99,106],"GMM-UBM":[12],"its":[14],"capacity":[15],"for":[16,96],"detection":[17],"robustness":[19],"speaker":[21,83,94],"recognition.":[22],"While":[23],"each":[24,31],"has":[26],"achieved":[27],"improvements":[28],"independent":[29,81,84],"other":[32],"in":[33,110],"an":[34],"orthogonal":[35],"field,":[36],"both":[37],"methods":[38],"have":[39],"a":[40],"similar":[41],"framework.":[42],"The":[43],"proposed":[44,101],"Signal":[45],"Bias":[46],"Removal":[47],"based":[48],"GMM":[49],"(SBR-GMM)":[50],"executes":[51],"minimization":[53],"environmental":[56],"variation":[57],"mismatched":[59],"condition":[60],"by":[61,129],"removing":[62],"bias":[64],"distorted":[67],"input":[68],"signal":[69],"adaptation":[72],"speaker-dependent":[75],"characteristics":[76],"from":[77],"clean,":[79],"text":[80],"background":[85],"GMM.":[86],"our":[88],"experiments,":[89],"compared":[91,118],"closed-set":[93],"identification":[95],"conventional":[97],"CMS":[98],"respectively":[103],"TIMIT":[105],"NTIMIT":[107],"database.":[108],"Particularly":[109],"third":[112],"set":[113],"experiments":[115],"NTIMIT,":[117],"to":[119,124],"CMS,":[120],"were":[122],"able":[123],"improve":[125],"recognition":[127],"rate":[128],"27.4%":[130],"using":[131],"robust":[133],"feature.":[134]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}