{"id":"https://openalex.org/W170726674","doi":"https://doi.org/10.21437/interspeech.2004-218","title":"Integration of articulatory dynamic parameters in HMM/BN based speech recognition system","display_name":"Integration of articulatory dynamic parameters in HMM/BN based speech recognition system","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W170726674","doi":"https://doi.org/10.21437/interspeech.2004-218","mag":"170726674"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-218","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["Advanced Telecommunications Research Institute International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Advanced Telecommunications Research Institute International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Japan Advanced Inst. of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Japan Advanced Inst. of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.313,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88935512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"564"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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":0.8448159694671631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7027822732925415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6900560855865479},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5412530303001404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4648396670818329},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.46159788966178894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42881494760513306},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.41176074743270874},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3838765621185303},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36070388555526733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35044917464256287}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8448159694671631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027822732925415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6900560855865479},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5412530303001404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4648396670818329},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.46159788966178894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42881494760513306},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.41176074743270874},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3838765621185303},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36070388555526733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35044917464256287},{"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-218","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.456.8984","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.456.8984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web-ext.u-aizu.ac.jp/~markov/pubs/ICSLP_04_2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W60893253","https://openalex.org/W185340767","https://openalex.org/W1564576422","https://openalex.org/W1967177300","https://openalex.org/W1986317063","https://openalex.org/W1998676560","https://openalex.org/W2039763773","https://openalex.org/W2132885390","https://openalex.org/W2151445288","https://openalex.org/W2158851235","https://openalex.org/W2159501365"],"related_works":["https://openalex.org/W2017210410","https://openalex.org/W1993009522","https://openalex.org/W1995792634","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2135672910","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870"],"abstract_inverted_index":{"In":[0,145],"this":[1],"paper,":[2],"we":[3,38,98],"describe":[4],"several":[5],"approaches":[6],"to":[7,88],"integra-tion":[8],"of":[9,33,47,69,116,162],"the":[10,70,80,95,101,114,117,124,138,156,163],"articulatory":[11,50,71,103,118],"dynamic":[12,54,119],"parameters":[13,55,106],"along":[14],"with":[15,49,147],"ar-ticulatory":[16],"position":[17,51,72],"data":[18,130,154],"into":[19],"a":[20,31],"HMM/BN":[21,81,157],"model":[22,83],"based":[23],"au-tomatic":[24],"speech":[25,42],"recognition":[26,164],"system.":[27],"This":[28],"work":[29],"is":[30,132],"contin-uation":[32],"our":[34],"previous":[35],"study,":[36],"where":[37,84],"have":[39],"successfully":[40],"combined":[41],"acoustic":[43,82,105,153],"features":[44,76,120],"in":[45,134],"form":[46],"MFCC":[48],"observations.":[52],"Articulatory":[53],"are":[56,77,107],"represented":[57],"by":[58],"velocity":[59],"and":[60,66,104,127],"acceleration":[61],"coefficients":[62],"calculated":[63],"as":[64],"first":[65],"second":[67],"derivatives":[68],"data.":[73],"All":[74],"these":[75],"in-tegrated":[78],"using":[79],"each":[85],"feature":[86],"corresponds":[87],"different":[89,142],"Bayesian":[90],"Network":[91],"vari-able.":[92],"By":[93],"changing":[94],"BN":[96,125],"topology":[97],"can":[99],"change":[100],"way":[102],"combined.":[108],"The":[109],"evaluation":[110],"experiments":[111],"showed":[112],"that":[113,128],"effect":[115],"greatly":[121],"depends":[122],"on":[123,152],"structure":[126],"careful":[129],"analysis":[131],"essential":[133],"gain-ing":[135],"knowledge":[136],"about":[137],"underlying":[139],"dependencies":[140],"be-tween":[141],"information":[143],"sources.":[144],"comparison":[146],"conventional":[148],"HMM":[149],"system":[150,158],"trained":[151],"only,":[155],"achieved":[159],"significant":[160],"improvement":[161],"performance.":[165],"1.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}