{"id":"https://openalex.org/W2112909784","doi":"https://doi.org/10.21437/interspeech.2008-104","title":"Discriminative training of variable-parameter HMMs for noise robust speech recognition","display_name":"Discriminative training of variable-parameter HMMs for noise robust speech recognition","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W2112909784","doi":"https://doi.org/10.21437/interspeech.2008-104","mag":"2112909784"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-104","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":true,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"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":"Li Deng","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"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":"Yifan Gong","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034476404"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.1061,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93823047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"288"},"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":0.9998000264167786,"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":0.9980999827384949,"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/discriminative-model","display_name":"Discriminative model","score":0.8694630861282349},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8028750419616699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6720561981201172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5652169585227966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5394585132598877},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5324733257293701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4729737341403961},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45693129301071167}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8694630861282349},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8028750419616699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720561981201172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652169585227966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5394585132598877},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5324733257293701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4729737341403961},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45693129301071167},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2008-104","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.7608","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.7608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/78268/VPHMM-Interspeech2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W180035620","https://openalex.org/W1982073070","https://openalex.org/W2050091530","https://openalex.org/W2125562481","https://openalex.org/W2169147844"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2162582511"],"abstract_inverted_index":{"We":[0,82],"propose":[1],"a":[2,19,86],"new":[3,38,61],"type":[4],"of":[5,22,47,52,138],"variable-parameter":[6,160],"hidden":[7,161],"Markov":[8,162],"model":[9,62,70,102],"(VPHMM)":[10],"whose":[11],"mean":[12,151],"and":[13,34,50,72,77,84,99,126,141,152],"variance":[14],"parameters":[15,71,80,93],"vary":[16],"each":[17],"as":[18],"continuous":[20],"function":[21],"additional":[23],"environmentdependent":[24],"parameters.":[25,58],"Different":[26],"from":[27],"the":[28,37,45,48,56,60,69,92,101,104,119,123,146],"polynomialfunction-based":[29],"VPHMM":[30,39,97],"proposed":[31,120],"by":[32],"Cui":[33],"Gong":[35],"(2007),":[36],"uses":[40],"cubic":[41,166],"splines":[42],"to":[43],"represent":[44],"dependency":[46],"means":[49],"variances":[51,153],"Gaussian":[53],"mixtures":[54],"on":[55,103],"environment":[57],"Importantly,":[59],"no":[63],"longer":[64],"requires":[65],"quantization":[66],"in":[67,94],"estimating":[68],"it":[73],"supports":[74],"parameter":[75],"sharing":[76],"instantaneous":[78],"conditioning":[79],"directly.":[81],"develop":[83],"describe":[85],"growth-transformation":[87],"algorithm":[88],"that":[89,118],"discriminatively":[90,124],"learns":[91],"our":[95,108],"cubic-splinebased":[96],"(CS-VPHMM),":[98],"evaluate":[100],"Aurora-3":[105],"corpus":[106],"with":[107,131],"recently":[109],"developed":[110],"MFCC-MMSE":[111],"noise":[112],"suppressor":[113],"applied.":[114],"Our":[115],"experiments":[116],"show":[117],"CS-VPHMM":[121],"outperforms":[122],"trained":[125,128],"maximum-likelihood":[127],"conventional":[129],"HMMs":[130],"relative":[132],"word":[133],"error":[134],"rate":[135],"(WER)":[136],"reduction":[137],"14":[139],"%":[140,143],"20":[142],"respectively":[144],"under":[145],"well-matched":[147],"conditions":[148],"when":[149],"both":[150],"are":[154],"updated.":[155],"Index":[156],"Terms:":[157],"speech":[158],"recognition,":[159],"model,":[163],"discriminative":[164],"training,":[165],"spline,":[167],"growth":[168],"transformation":[169],"1.":[170]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}