{"id":"https://openalex.org/W2133239889","doi":"https://doi.org/10.21437/interspeech.2010-624","title":"FSM-based pronunciation modeling using articulatory phonological code","display_name":"FSM-based pronunciation modeling using articulatory phonological code","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2133239889","doi":"https://doi.org/10.21437/interspeech.2010-624","mag":"2133239889"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-624","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-624","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/2142/16726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112054566","display_name":"Chi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chi Hu","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112054566"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.8619,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88163359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2274","last_page":"2277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8701682090759277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8073362112045288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.676925539970398},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5634663701057434},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49662119150161743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44030192494392395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42493346333503723},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11469435691833496},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09277495741844177}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8701682090759277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073362112045288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.676925539970398},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5634663701057434},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49662119150161743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44030192494392395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42493346333503723},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11469435691833496},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09277495741844177},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":3,"locations":[{"id":"doi:10.21437/interspeech.2010-624","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-624","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:www.ideals.illinois.edu:2142/16726","is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/16726","pdf_url":"http://hdl.handle.net/2142/16726","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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:10.1.1.294.6798","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.6798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2010/hu10interspeech.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/16726","is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/16726","pdf_url":"http://hdl.handle.net/2142/16726","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2133239889.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W33424208","https://openalex.org/W108207029","https://openalex.org/W120411324","https://openalex.org/W150312962","https://openalex.org/W198572130","https://openalex.org/W1527878980","https://openalex.org/W1625762979","https://openalex.org/W1970996882","https://openalex.org/W2015073768","https://openalex.org/W2027297142","https://openalex.org/W2048449762","https://openalex.org/W2049633694","https://openalex.org/W2052382192","https://openalex.org/W2068447135","https://openalex.org/W2091650508","https://openalex.org/W2105738468","https://openalex.org/W2106392848","https://openalex.org/W2126106809","https://openalex.org/W2130607791","https://openalex.org/W2141825426","https://openalex.org/W2148226542","https://openalex.org/W2990032170"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W1997182898","https://openalex.org/W2296205523"],"abstract_inverted_index":{"According":[0],"to":[1,32,45,91,132,157],"articulatory":[2],"phonology,":[3],"the":[4,13,17,26,36,47,93,100,112,144,154,158,168,191,233],"gestural":[5,22,49,62,97,102,135,146,160,235],"score":[6,63,103],"is":[7,130,150,174],"an":[8,176],"invariant":[9],"speech":[10,37,164],"representation.":[11],"Though":[12],"timing":[14,67,137],"schemes,":[15],"i.e.,":[16],"onsets":[18,115],"and":[19,116,121,180],"offsets,":[20],"of
\\nthe":[21],"activations":[23,30,50,156],"may":[24],"vary,":[25],"ensemble":[27],"of":[28,95,104,162,171,222,232],"these":[29],"tends":[31],"remain":[33],"unchanged,":[34],"informing":[35],"content.":[38],"\"Gestural":[39],"pattern":[40],"vector\"
\\n(GPV)":[41],"has":[42],"been":[43],"proposed":[44,212],"encode":[46],"instantaneous":[48],"that":[51,84,139],"exist":[52],"across":[53],"all":[54],"tract":[55],"variables":[56],"at":[57],"each":[58,172],"time.":[59],"Therefore,":[60],"a":[61,65,73,80,86,96,105,108,124,196,220],"with":[64,107,190,225],"particular":[66],"scheme":[68],"can":[69],"be":[70],"approximated":[71],"using":[72,205],"GPV":[74,173],"sequence.
\\n
\\nIn":[75],"this":[76],"work,":[77],"we":[78],"propose":[79],"pronunciation":[81,193,213],"modeling":[82,214],"method":[83],"uses":[85],"finite":[87],"state":[88],"machine":[89],"(FSM)":[90],"represent":[92],"invariance":[94],"score.":[98,147,236],"Given":[99],"\"canonical\"":[101,145,234],"word":[106,202],"known":[109],"activation":[110,114,136],"timing
\\nscheme,":[111],"plausible":[113],"offsets":[117],"are":[118,187],"recursively":[119],"generated":[120],"encoded":[122],"as":[123],"weighted":[125],"FSM.":[126],"An":[127],"empirical":[128],"measure":[129],"used":[131,188],"prune":[133],"out":[134,200],"schemes":[138],"deviate":[140],"too":[141],"much":[142],"from":[143,208],"Speech":[148],"recognition":[149],"achieved":[151],"by":[152],"matching":[153],"recovered
\\ngestural":[155],"FSM-encoded":[159],"scores":[161],"different":[163],"contents.":[165],"In":[166],"particular,":[167],"observation":[169],"distribution":[170],"modeled
\\nby":[175],"artificial":[177],"neural":[178],"network":[179],"Gaussian":[181],"mixture":[182],"tandem":[183],"model.":[184],"These":[185],"models":[186,194],"together":[189],"FSM-based":[192],"in":[195],"Bayesian":[197],"framework.
\\n
\\nWe":[198],"carry":[199],"pilot":[201],"classification":[203],"experiments":[204],"synthesized":[206],"data":[207],"one":[209],"speaker.":[210],"The":[211],"achieves":[215],"over":[216],"90%":[217],"accuracy":[218],"for":[219],"vocabulary":[221],"139":[223],"words":[224],"no":[226],"training":[227],"observations,":[228],"outperforming":[229],"direct":[230],"use":[231]},"counts_by_year":[{"year":2015,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}