{"id":"https://openalex.org/W2103295509","doi":"https://doi.org/10.1109/asru.2007.4430133","title":"Bayesian adaptation in HMM training and decoding using a mixture of feature transforms","display_name":"Bayesian adaptation in HMM training and decoding using a mixture of feature transforms","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2103295509","doi":"https://doi.org/10.1109/asru.2007.4430133","mag":"2103295509"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5073006801","display_name":"Stavros Tsakalidis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117418","display_name":"Babraham Bioscience Technologies (United Kingdom)","ror":"https://ror.org/02b4c4128","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210117418"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Tsakalidis","raw_affiliation_strings":["BBN Technologies, Inc., Cambridge, MA, USA","BBN Technol., Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, Inc., Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge","institution_ids":["https://openalex.org/I4210117418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117418","display_name":"Babraham Bioscience Technologies (United Kingdom)","ror":"https://ror.org/02b4c4128","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210117418"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":["BBN Technologies, Inc., Cambridge, MA, USA","BBN Technol., Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, Inc., Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge","institution_ids":["https://openalex.org/I4210117418"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210117418"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"329","last_page":"334"},"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":0.9987000226974487,"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":0.9926000237464905,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.633983850479126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129248142242432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5934047102928162},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5860435366630554},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5388703942298889},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5289623141288757},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.505247175693512},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.47535035014152527},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4681439995765686},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4258752465248108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39182788133621216}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.633983850479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129248142242432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5934047102928162},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5860435366630554},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5388703942298889},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5289623141288757},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.505247175693512},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.47535035014152527},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4681439995765686},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4258752465248108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39182788133621216},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W51652730","https://openalex.org/W117579468","https://openalex.org/W1599512239","https://openalex.org/W2002342963","https://openalex.org/W2049633694","https://openalex.org/W2114973313","https://openalex.org/W2121546856","https://openalex.org/W2128014038","https://openalex.org/W2146871184","https://openalex.org/W2157084746","https://openalex.org/W2169042847","https://openalex.org/W2308181013","https://openalex.org/W6602068693","https://openalex.org/W6679093997","https://openalex.org/W6683389223"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2964314781","https://openalex.org/W4389708677","https://openalex.org/W3006565005","https://openalex.org/W4287868071","https://openalex.org/W2611832276","https://openalex.org/W69468016","https://openalex.org/W2007093222"],"abstract_inverted_index":{"Adaptive":[0],"training":[1,123],"under":[2],"a":[3,31,38,70,85],"Bayesian":[4,28,51],"framework":[5,29,52],"addresses":[6],"some":[7],"limitations":[8],"of":[9,33,72,79,88,99],"the":[10,16,34,46,50,66,77,89,100,103,109],"standard":[11,139],"maximum":[12],"likelihood":[13,78,120],"approaches.":[14],"Also,":[15],"adaptively":[17],"trained":[18],"system":[19],"can":[20],"be":[21],"directly":[22],"used":[23],"in":[24,102],"unsupervised":[25],"inference.":[26],"The":[27],"uses":[30],"distribution":[32,44,68],"transform":[35,43,67,110],"rather":[36],"than":[37],"point":[39],"estimate.":[40],"A":[41],"continuous":[42],"makes":[45],"integral":[47],"associated":[48],"with":[49,105],"intractable":[53],"and":[54,125,138],"therefore":[55],"various":[56],"approximations":[57],"have":[58],"been":[59],"proposed.":[60],"In":[61],"this":[62,75],"paper":[63],"we":[64],"model":[65],"via":[69],"mixture":[71],"transforms.":[73],"Under":[74],"model,":[76],"an":[80],"utterance":[81],"is":[82],"computed":[83],"as":[84],"weighted":[86],"sum":[87],"likelihoods":[90],"obtained":[91],"by":[92],"transforming":[93],"its":[94],"features":[95],"based":[96],"on":[97,114,121,130],"each":[98],"transforms":[101],"mixture,":[104],"weights":[106],"set":[107],"to":[108,135],"priors.":[111],"Experimental":[112],"results":[113],"Arabic":[115],"broadcast":[116],"news":[117],"exhibit":[118],"increased":[119],"acoustic":[122],"data":[124],"improved":[126],"speech":[127],"recognition":[128],"performance":[129],"unseen":[131],"test":[132],"data,":[133],"compared":[134],"speaker":[136],"independent":[137],"adaptive":[140],"models.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}