{"id":"https://openalex.org/W2144049961","doi":"https://doi.org/10.1109/icassp.2011.5947493","title":"Bayesian sensing hidden Markov models for speech recognition","display_name":"Bayesian sensing hidden Markov models for speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2144049961","doi":"https://doi.org/10.1109/icassp.2011.5947493","mag":"2144049961"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947493","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/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"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":["National Cheng Kung University, Tainan, Taiwan","National Cheng Kung University, Tainan, Taiwan 70101, ROC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"National Cheng Kung University, Tainan, Taiwan 70101, ROC","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5056","last_page":"5059"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9957000017166138,"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":0.8686062097549438},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8381561040878296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7146470546722412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6400632858276367},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5874892473220825},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5462980270385742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5451471209526062},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5272461771965027},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5169991254806519},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4845086932182312},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.43962424993515015},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4320521652698517},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.41556182503700256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3898114562034607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2811990976333618},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.27917975187301636},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12288731336593628}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8686062097549438},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8381561040878296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7146470546722412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6400632858276367},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5874892473220825},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5462980270385742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5451471209526062},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5272461771965027},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5169991254806519},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4845086932182312},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.43962424993515015},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4320521652698517},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.41556182503700256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3898114562034607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2811990976333618},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.27917975187301636},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12288731336593628},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947493","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1663973292","https://openalex.org/W2002342963","https://openalex.org/W2034870236","https://openalex.org/W2067474491","https://openalex.org/W2071284784","https://openalex.org/W2125234026","https://openalex.org/W2125610823","https://openalex.org/W2135346345","https://openalex.org/W2142084376","https://openalex.org/W2151402979","https://openalex.org/W2151485937","https://openalex.org/W2594639291","https://openalex.org/W4285719527","https://openalex.org/W6678457041"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W1839961359","https://openalex.org/W1595191759","https://openalex.org/W2343819364","https://openalex.org/W2133205540","https://openalex.org/W2075146114","https://openalex.org/W2046798682","https://openalex.org/W2010299594","https://openalex.org/W2100805585"],"abstract_inverted_index":{"We":[0,80],"introduce":[1],"Bayesian":[2],"sensing":[3,26,56,98],"hidden":[4],"Markov":[5],"models":[6,115],"(BS-HMMs)":[7],"to":[8,34],"represent":[9],"speech":[10],"data":[11],"based":[12],"on":[13,102],"a":[14,31,93],"set":[15],"of":[16,25,30,48,55,62,96],"state-dependent":[17],"basis":[18,50],"vectors.":[19],"By":[20],"incorporating":[21],"the":[22,28,40,49,52,59,70,77,85,97],"prior":[23],"density":[24],"weights,":[27],"relevance":[29],"feature":[32],"vector":[33],"different":[35],"bases":[36],"is":[37,74],"determined":[38],"by":[39,68],"corresponding":[41],"precision":[42,53,60],"parameters.":[43],"The":[44],"BS-HMM":[45],"parameters,":[46,87],"consisting":[47],"vectors,":[51],"matrices":[54,61],"weights":[57],"and":[58,119],"reconstruction":[63],"errors,":[64],"are":[65,89],"jointly":[66],"estimated":[67],"maximizing":[69],"likelihood":[71],"function,":[72],"which":[73,88],"marginalized":[75],"over":[76,109],"weight":[78],"priors.":[79],"derive":[81],"recursive":[82],"solutions":[83],"for":[84,116],"three":[86],"expressed":[90],"via":[91],"maximum":[92],"posteriori":[94],"estimates":[95],"weights.":[99],"Experimental":[100],"results":[101],"an":[103],"LVCSR":[104],"task":[105],"show":[106],"consistent":[107],"gains":[108],"conventional":[110],"HMMs":[111],"with":[112],"Gaussian":[113],"mixture":[114],"both":[117],"ML":[118],"discriminative":[120],"training":[121],"scenarios.":[122]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}