{"id":"https://openalex.org/W2142825941","doi":"https://doi.org/10.1109/icassp.2009.4960446","title":"Bayesian large margin hidden Markov models for speech recognition","display_name":"Bayesian large margin hidden Markov models for speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2142825941","doi":"https://doi.org/10.1109/icassp.2009.4960446","mag":"2142825941"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5028824941","display_name":"Jung-Chun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jung-Chun Chen","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan, ROC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028824941"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":1.7447,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87728719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"3765","last_page":"3768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.996999979019165,"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":0.9940000176429749,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8343278169631958},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8188244104385376},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6779083013534546},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6548964381217957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6332625150680542},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5933647155761719},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5581983327865601},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4673376977443695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4553464353084564},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.45448729395866394}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8343278169631958},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8188244104385376},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6779083013534546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6548964381217957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6332625150680542},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5933647155761719},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5581983327865601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4673376977443695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4553464353084564},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.45448729395866394}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1663973292","https://openalex.org/W2104997912","https://openalex.org/W2111421849","https://openalex.org/W2111479622","https://openalex.org/W2115979064","https://openalex.org/W2139890545","https://openalex.org/W2141212024","https://openalex.org/W2142084376","https://openalex.org/W2148603752","https://openalex.org/W2158289097","https://openalex.org/W2165058613","https://openalex.org/W2167270514","https://openalex.org/W2170918767","https://openalex.org/W2911546748","https://openalex.org/W6675604347","https://openalex.org/W6680892293"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2053269318","https://openalex.org/W2110523656","https://openalex.org/W1487808658"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,51,99],"Bayesian":[4,22,41,61],"learning":[5],"approach":[6],"to":[7,74,105],"large":[8,23,62],"margin":[9,24,63,85],"classifier":[10],"for":[11,32],"hidden":[12],"Markov":[13],"model":[14,30,108],"(HMM)":[15],"based":[16],"speech":[17],"recognition.":[18],"We":[19],"build":[20],"the":[21,29,39,55,76],"HMMs":[25],"(BLM-HMMs)":[26],"and":[27,71,86,110,125],"improve":[28],"generalization":[31],"handling":[33],"unknown":[34],"test":[35],"environments.":[36],"Using":[37],"BLM-HMMs,":[38],"variational":[40],"HMM":[42,58],"parameters":[43],"are":[44],"estimated":[45],"by":[46],"maximizing":[47],"lower":[48],"bound":[49],"of":[50,57,78],"marginal":[52],"likelihood":[53],"over":[54],"uncertainties":[56],"parameters.":[59],"The":[60,90],"estimation":[64],"is":[65,72,94],"performed":[66],"with":[67,107],"frame":[68],"selection":[69,109],"mechanism,":[70],"illustrated":[73],"meet":[75],"objective":[77,92],"support":[79],"vector":[80],"machines,":[81],"i.e.":[82],"maximal":[83],"class":[84],"minimal":[87],"training":[88],"errors.":[89],"new":[91],"function":[93],"not":[95],"only":[96],"interpreted":[97],"as":[98],"discriminative":[100,126],"criterion,":[101],"but":[102],"also":[103],"feasible":[104],"deal":[106],"adaptive":[111],"training.":[112],"Experiments":[113],"on":[114],"phone":[115],"recognition":[116],"show":[117],"that":[118],"BLM-HMMs":[119],"perform":[120],"better":[121],"than":[122],"other":[123],"generative":[124],"models.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}