{"id":"https://openalex.org/W1590906142","doi":"https://doi.org/10.21437/interspeech.2010-604","title":"HMM-based text-to-articulatory-movement prediction and analysis of critical articulators","display_name":"HMM-based text-to-articulatory-movement prediction and analysis of critical articulators","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1590906142","doi":"https://doi.org/10.21437/interspeech.2010-604","mag":"1590906142"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-604","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/4563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["School of Informatics, Institute of Language, Cognition and Computation"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Institute of Language, Cognition and Computation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics, Institute of Language, Cognition and Computation"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Institute of Language, Cognition and Computation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059767940"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3383,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53035306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2194","last_page":"2197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987000226974487,"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":0.9983999729156494,"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":0.9081197381019592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7158976793289185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6574441194534302},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.609497606754303},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5650275945663452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4527018070220947},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4373810887336731},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4310312271118164},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4297845959663391},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38543498516082764},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.23047751188278198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1903136670589447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17225179076194763},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12950760126113892}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9081197381019592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158976793289185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6574441194534302},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.609497606754303},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5650275945663452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4527018070220947},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4373810887336731},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4310312271118164},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4297845959663391},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38543498516082764},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.23047751188278198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1903136670589447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17225179076194763},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12950760126113892},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-604","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/4563","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4563","pdf_url":"http://hdl.handle.net/1842/4563","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:publications/5f7635de-7c8e-4161-a1f6-ba4154faf0f8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/5f7635de-7c8e-4161-a1f6-ba4154faf0f8","pdf_url":"http://www.isca-speech.org/archive/archive_papers/interspeech_2010/i10_1974.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.1529","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.1529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2010/IS100349.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/4563","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4563","pdf_url":"http://hdl.handle.net/1842/4563","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1590906142.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W133559434","https://openalex.org/W1529897604","https://openalex.org/W1878590289","https://openalex.org/W1963627370","https://openalex.org/W2013317861","https://openalex.org/W2034829178","https://openalex.org/W2068476922","https://openalex.org/W2090404765","https://openalex.org/W2105478683","https://openalex.org/W2154920538","https://openalex.org/W2400063444","https://openalex.org/W3031363333"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2194396582","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2379938888","https://openalex.org/W2566202039","https://openalex.org/W4233405330","https://openalex.org/W2792905593"],"abstract_inverted_index":{"In":[0,66],"this":[1],"paper":[2],"we":[3,69,106],"present":[4],"a":[5,12,26,46,123],"method":[6],"to":[7,37,61,109],"predict":[8,41],"the":[9,53,111,128,140],"movement":[10],"of":[11,28,88,130],"speaker\u2019s":[13],"mouth":[14],"from":[15,44,95],"text":[16],"input":[17],"using":[18],"hidden":[19],"Markov":[20],"models":[21,74],"(HMM).":[22],"We":[23,121],"have":[24],"used":[25,60],"corpus":[27],"human":[29],"articulatory":[30,42,64],"movements,":[31],"recorded":[32],"by":[33],"electromagnetic":[34],"articulography":[35],"(EMA),":[36],"train":[38],"HMMs.":[39],"To":[40],"movements":[43,129],"text,":[45,96],"suitable":[47],"model":[48],"sequence":[49],"is":[50,59],"selected":[51],"and":[52,77,97,118],"maximum-likelihood":[54],"parameter":[55],"generation":[56],"(MLPG)":[57],"algorithm":[58],"generate":[62],"output":[63],"trajectories.":[65],"our":[67],"experiments,":[68],"find":[70,122],"that":[71,127],"fully":[72],"context-dependent":[73],"outperform":[75],"monophone":[76],"quinphone":[78],"models,":[79],"achieving":[80],"an":[81],"average":[82,141],"root":[83],"mean":[84],"square":[85],"(RMS)":[86],"error":[87,113],"1.945mm":[89],"when":[90,99],"state":[91,101],"durations":[92,102],"are":[93,103],"predicted":[94,136],"0.872mm":[98],"natural":[100],"used.":[104],"Finally,":[105],"go":[107],"on":[108],"analyze":[110],"prediction":[112],"for":[114],"different":[115],"EMA":[116],"dimensions":[117],"phone":[119],"types.":[120],"clear":[124],"pattern":[125],"emerges":[126],"so-called":[131],"critical":[132],"articulators":[133],"can":[134],"be":[135],"more":[137],"accurately":[138],"than":[139],"performance.":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}