{"id":"https://openalex.org/W2135346345","doi":"https://doi.org/10.1109/icassp.2011.5947558","title":"Discriminative training for Bayesian sensing hidden Markov models","display_name":"Discriminative training for Bayesian sensing hidden Markov models","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2135346345","doi":"https://doi.org/10.1109/icassp.2011.5947558","mag":"2135346345"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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":["IBM Research, USA","National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5316","last_page":"5319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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":0.9159802198410034},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.859502911567688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7393773794174194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6921071410179138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6503905057907104},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6496851444244385},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6178063154220581},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5355700254440308},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5165104269981384},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4643004536628723},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.41550275683403015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38137638568878174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21813997626304626}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9159802198410034},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.859502911567688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7393773794174194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6921071410179138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6503905057907104},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6496851444244385},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6178063154220581},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5355700254440308},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5165104269981384},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4643004536628723},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.41550275683403015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38137638568878174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21813997626304626},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W43454013","https://openalex.org/W156213964","https://openalex.org/W1877570817","https://openalex.org/W2002342963","https://openalex.org/W2125234026","https://openalex.org/W2125610823","https://openalex.org/W2144049961","https://openalex.org/W2150907703","https://openalex.org/W2164225659","https://openalex.org/W4285719527","https://openalex.org/W6678457041","https://openalex.org/W6682398751"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2167155152","https://openalex.org/W4324119469","https://openalex.org/W2146591867","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2075383893","https://openalex.org/W156213964","https://openalex.org/W2050960118"],"abstract_inverted_index":{"We":[0],"describe":[1],"feature":[2,40,86],"space":[3,6],"and":[4,58],"model":[5],"discriminative":[7,85],"training":[8,81],"for":[9],"a":[10,30,39,71,125],"new":[11],"class":[12],"of":[13,32,38,51,62,82],"acoustic":[14],"models":[15,21,105,114],"called":[16],"Bayesian":[17],"sensing":[18,53],"hidden":[19],"Markov":[20],"(BS-HMMs).":[22],"In":[23],"BS-HMMs,":[24],"speech":[25],"data":[26],"is":[27,45],"represented":[28],"by":[29,47,69],"set":[31],"state-dependent":[33],"basis":[34,56],"vectors.":[35],"The":[36,55],"relevance":[37],"vector":[41],"to":[42,120],"different":[43,136],"bases":[44],"determined":[46],"the":[48,52,59,63,80,89,103,117,121,132],"precision":[49,60],"matrices":[50,61],"weights.":[54],"vectors":[57],"reconstruction":[64],"errors":[65],"are":[66],"jointly":[67],"estimated":[68],"optimizing":[70],"maximum":[72],"mutual":[73],"information":[74],"(MMI)":[75],"criterion.":[76],"Additionally,":[77],"we":[78],"discuss":[79],"an":[83,98],"fMPE-style":[84],"transformation":[87],"under":[88],"same":[90],"criterion":[91],"given":[92],"these":[93],"models.":[94],"Experimental":[95],"results":[96],"on":[97],"LVCSR":[99],"task":[100],"show":[101],"that":[102,131],"proposed":[104],"outperform":[106],"discriminatively":[107],"trained":[108],"conventional":[109],"HMMs":[110],"with":[111],"Gaussian":[112],"mixture":[113],"(GMMs).":[115],"Cross-adapting":[116],"baseline":[118],"GMM-HMMs":[119],"BS-HMM":[122],"output":[123],"yields":[124],"6%":[126],"relative":[127],"gain":[128],"which":[129],"indicates":[130],"two":[133],"systems":[134],"make":[135],"errors.":[137]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}