{"id":"https://openalex.org/W60893253","doi":"https://doi.org/10.21437/eurospeech.2003-334","title":"Hybrid HMM/BN ASR system integrating spectrum and articulatory features","display_name":"Hybrid HMM/BN ASR system integrating spectrum and articulatory features","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W60893253","doi":"https://doi.org/10.21437/eurospeech.2003-334","mag":"60893253"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-334","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009565318","display_name":"Yosuke Iizuka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Iizuka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2195,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93844649,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"968"},"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":0.9986000061035156,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.897515058517456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.78862464427948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7876421213150024},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5637509226799011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5204770565032959},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4793987274169922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46173039078712463},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4591268002986908},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4497588872909546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43987327814102173},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08786085247993469}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.897515058517456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78862464427948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7876421213150024},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5637509226799011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5204770565032959},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4793987274169922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46173039078712463},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4591268002986908},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4497588872909546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43987327814102173},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08786085247993469},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-334","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W185340767","https://openalex.org/W1564576422","https://openalex.org/W1581928298","https://openalex.org/W1586645951","https://openalex.org/W1998676560","https://openalex.org/W2151445288","https://openalex.org/W2159501365"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2185075503","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W4229940372","https://openalex.org/W2186375278"],"abstract_inverted_index":{"In":[0,58,107],"this":[1],"paper,":[2],"we":[3,110],"describe":[4],"automatic":[5],"speech":[6,14,50],"recognition":[7,32,91,113],"system":[8,16,35,86,121],"where":[9],"features":[10,51,60],"extracted":[11],"from":[12],"human":[13],"production":[15],"in":[17,26,77,89,101],"form":[18],"of":[19,48,82,97,126],"articulatory":[20,62],"movements":[21],"data":[22,100],"are":[23,65],"effectively":[24],"integrated":[25],"the":[27,39,80,123],"acoustic":[28],"model":[29],"for":[30,45],"improved":[31],"performance.":[33],"The":[34,85],"is":[36],"based":[37,119],"on":[38,93],"hybrid":[40],"HMM/BN":[41],"model,":[42],"which":[43,64],"allows":[44],"easy":[46],"integration":[47],"different":[49],"by":[52],"modeling":[53],"probabilistic":[54],"dependencies":[55],"between":[56],"them.":[57],"addition,":[59],"like":[61],"movements,":[63],"difficult":[66],"or":[67],"impossible":[68],"to":[69,116],"obtain":[70],"during":[71],"recognition,":[72],"can":[73],"be":[74],"left":[75],"hidden,":[76],"fact":[78],"eliminating":[79],"need":[81],"their":[83],"extraction.":[84],"was":[87],"evaluated":[88],"phoneme":[90],"task":[92],"small":[94],"database":[95],"consisting":[96],"three":[98],"speakers\u2019":[99],"speaker":[102],"dependent":[103],"and":[104],"multi-speaker":[105],"modes.":[106],"both":[108],"cases,":[109],"obtained":[111],"higher":[112],"rates":[114],"compared":[115],"conventional,":[117],"spectrum":[118],"HMM":[120],"with":[122],"same":[124],"number":[125],"parameters.":[127]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}