{"id":"https://openalex.org/W2144434023","doi":"https://doi.org/10.1109/icassp.2004.1326164","title":"Minimum Kullback-Leibler distance based multivariate Gaussian feature adaptation for distant-talking speech recognition","display_name":"Minimum Kullback-Leibler distance based multivariate Gaussian feature adaptation for distant-talking speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2144434023","doi":"https://doi.org/10.1109/icassp.2004.1326164","mag":"2144434023"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5100720369","display_name":"Yue Pan","orcid":"https://orcid.org/0000-0001-6019-065X"},"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":"Yue Pan","raw_affiliation_strings":["Interactive System Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA","Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive System Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA#TAB#","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":"A. Waibel","raw_affiliation_strings":["Interactive System Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA","Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive System Laboratories, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"1029"},"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":0.9991000294685364,"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":0.998199999332428,"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":0.7742793560028076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7034255266189575},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.6032931208610535},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5688209533691406},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.5201361775398254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5007686614990234},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4999690055847168},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.49351346492767334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48374247550964355},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4652387201786041},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46309590339660645},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43097299337387085},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4150618314743042},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4140307307243347},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.41151198744773865},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3917621970176697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2272646427154541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742793560028076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7034255266189575},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.6032931208610535},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5688209533691406},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5201361775398254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5007686614990234},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4999690055847168},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.49351346492767334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48374247550964355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4652387201786041},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46309590339660645},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43097299337387085},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4150618314743042},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4140307307243347},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.41151198744773865},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3917621970176697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2272646427154541},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1656317801","https://openalex.org/W1843554590","https://openalex.org/W2146871184"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":{"Multivariate":[0],"Gaussian":[1,45],"based":[2,57,126,133],"speech":[3,21,115,143],"compensation":[4],"or":[5],"mapping":[6,25],"has":[7],"been":[8],"developed":[9],"to":[10,52,75],"reduce":[11],"the":[12,54,60,64,100,103,131],"mismatch":[13],"between":[14,63],"training":[15],"and":[16,69,117],"deployment":[17],"conditions":[18],"for":[19,138],"robust":[20],"recognition.":[22],"The":[23,128],"acoustic":[24,67],"procedure":[26],"can":[27],"be":[28],"formulated":[29],"as":[30],"a":[31,36,43,49,85,107,113,139],"feature":[32,87],"space":[33],"adaptation":[34],"where":[35],"noisy":[37],"input":[38],"signal":[39],"is":[40,73,96,135],"transformed":[41,70],"by":[42],"multivariate":[44],"network.":[46],"We":[47,98],"propose":[48],"novel":[50],"algorithm":[51,105],"update":[53],"network":[55],"parameters":[56],"on":[58,84,112],"minimizing":[59],"Kullback-Leibler":[61],"distance":[62],"core":[65],"recognizer's":[66],"model":[68],"features.":[71],"It":[72],"designed":[74],"achieve":[76],"optimal":[77],"overall":[78],"system":[79,111],"performance":[80,101,120],"rather":[81],"than":[82],"MMSE":[83,125],"specific":[86],"domain.":[88],"An":[89],"online":[90],"stochastic":[91],"gradient":[92],"descent":[93],"learning":[94],"rule":[95],"derived.":[97],"evaluate":[99],"of":[102,123],"new":[104],"using":[106],"JRTk":[108],"broadcast":[109],"news":[110],"distance-talking":[114],"corpus":[116],"compare":[118],"its":[119],"with":[121],"that":[122],"previous":[124],"approaches.":[127],"experiments":[129],"show":[130],"KL":[132],"approach":[134],"more":[136],"effective":[137],"large":[140],"vocabulary":[141],"continuous":[142],"recognition":[144],"(LVCSR)":[145],"system.":[146]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}