{"id":"https://openalex.org/W2126749346","doi":"https://doi.org/10.1109/asru.2009.5373359","title":"A study on hidden Markov model's generalization capability for speech recognition","display_name":"A study on hidden Markov model's generalization capability for speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2126749346","doi":"https://doi.org/10.1109/asru.2009.5373359","mag":"2126749346"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","School of Computer Engineering, Nanyang Technological University, Singapore, 639798"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore, 639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corp., Redmond, WA 98052, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","School of Computer Engineering, Nanyang Technological University, Singapore, 639798"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore, 639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","[Institute for Infocomm Research, Singapore 138632.]"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"[Institute for Infocomm Research, Singapore 138632.]","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, 30332, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101602536"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80770765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"255","last_page":"260"},"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":0.9995999932289124,"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":0.995199978351593,"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":0.7817639112472534},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.778423547744751},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7597147226333618},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6944673657417297},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5760003328323364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.549124538898468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5332690477371216},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5292842984199524},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4805060625076294},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4642069935798645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44903185963630676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44070571660995483},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.42241784930229187},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16539186239242554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817639112472534},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.778423547744751},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7597147226333618},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6944673657417297},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5760003328323364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.549124538898468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5332690477371216},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5292842984199524},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4805060625076294},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4642069935798645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44903185963630676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44070571660995483},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.42241784930229187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16539186239242554},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W111968546","https://openalex.org/W1877570817","https://openalex.org/W2033565080","https://openalex.org/W2063541597","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2080921589","https://openalex.org/W2100969003","https://openalex.org/W2104997912","https://openalex.org/W2105613180","https://openalex.org/W2105885996","https://openalex.org/W2111479622","https://openalex.org/W2134218976","https://openalex.org/W2136386449","https://openalex.org/W2146871184","https://openalex.org/W2150142469","https://openalex.org/W2150252476","https://openalex.org/W2151484683","https://openalex.org/W2156909104","https://openalex.org/W2158289097","https://openalex.org/W2159112514","https://openalex.org/W6675604347","https://openalex.org/W6682334925"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W1617617605","https://openalex.org/W203970584","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"From":[0],"statistical":[1],"learning":[2],"theory,":[3],"the":[4,11,22,26,49,63,73,79,100,108,111,121,140,148,156,160,172,201,212,227],"generalization":[5,33,70,105,123,173,216],"capability":[6,34,124,174,217],"of":[7,51,99,102,110,129,214],"a":[8],"model":[9,66],"is":[10,136,176,187,198],"ability":[12],"to":[13,61,154,158,180,210],"generalize":[14],"well":[15],"on":[16,85,185],"unseen":[17],"test":[18],"data":[19,43,157],"which":[20],"follow":[21],"same":[23],"distribution":[24],"as":[25,171],"training":[27,42,56,141],"data.":[28,144],"This":[29],"paper":[30],"investigates":[31],"how":[32],"can":[35],"also":[36,146,207],"improve":[37],"robustness":[38,128,220],"when":[39,134],"testing":[40,143],"and":[41,78,92,142,150,166,191,230],"are":[44,59,94,233],"from":[45,189],"different":[46],"distributions":[47],"in":[48,96,218,221],"context":[50],"speech":[52,130],"recognition.":[53],"Two":[54],"discriminative":[55],"(DT)":[57],"methods":[58],"used":[60],"train":[62],"hidden":[64],"Markov":[65],"(HMM)":[67],"for":[68],"better":[69,122,127,170,215],"capability,":[71,106],"namely":[72],"minimum":[74],"classification":[75],"error":[76,195],"(MCE)":[77],"soft-margin":[80],"estimation":[81],"(SME)":[82],"methods.":[83],"Results":[84],"Aurora-2":[86,186],"task":[87,225],"show":[88],"that":[89],"both":[90],"SME":[91,114,167,190,209],"MCE":[93,165],"effective":[95],"improving":[97,219],"one":[98],"measures":[101],"acoustic":[103],"model's":[104],"i.e.":[107],"margin":[109],"model,":[112],"with":[113],"be":[115],"moderately":[116],"more":[117,177,222],"effective.":[118],"In":[119],"addition,":[120],"translates":[125],"into":[126],"recognition":[131],"performance,":[132],"even":[133,169],"there":[135],"significant":[137,231],"mismatch":[138],"between":[139],"We":[145],"applied":[147],"mean":[149],"variance":[151],"normalization":[152],"(MVN)":[153],"preprocess":[155],"reduce":[159],"training-testing":[161],"mismatch.":[162],"After":[163],"MVN,":[164],"perform":[168],"now":[175],"closely":[178],"related":[179],"robustness.":[181],"The":[182],"best":[183],"performance":[184],"obtained":[188],"about":[192],"28%":[193],"relative":[194],"rate":[196],"reduction":[197],"achieved":[199],"over":[200],"MVN":[202],"baseline":[203],"system.":[204],"Finally,":[205],"we":[206],"use":[208],"demonstrate":[211],"potential":[213],"realistic":[223],"noisy":[224],"using":[226],"Aurora-3":[228],"task,":[229],"improvements":[232],"obtained.":[234]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}