{"id":"https://openalex.org/W2123778414","doi":"https://doi.org/10.1186/1687-4722-2014-23","title":"Identifying underlying articulatory targets of Thai vowels from acoustic data based on an analysis-by-synthesis approach","display_name":"Identifying underlying articulatory targets of Thai vowels from acoustic data based on an analysis-by-synthesis approach","publication_year":2014,"publication_date":"2014-05-08","ids":{"openalex":"https://openalex.org/W2123778414","doi":"https://doi.org/10.1186/1687-4722-2014-23","mag":"2123778414"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2014-23","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-23","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-23","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-23","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003455071","display_name":"Santitham Prom\u2013on","orcid":"https://orcid.org/0000-0002-0869-089X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["GB","TH"],"is_corresponding":true,"raw_author_name":"Santitham Prom-on","raw_affiliation_strings":["Department of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, 10140, Thailand","Department of Speech, Hearing and Phonetic Sciences, University College London, London, WC1N 1PF, UK","Department of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","Department of Speech, Hearing and Phonetic Sciences, University College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, 10140, Thailand","institution_ids":["https://openalex.org/I60837268"]},{"raw_affiliation_string":"Department of Speech, Hearing and Phonetic Sciences, University College London, London, WC1N 1PF, UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Department of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]},{"raw_affiliation_string":"Department of Speech, Hearing and Phonetic Sciences, University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046141664","display_name":"Peter Birkholz","orcid":"https://orcid.org/0000-0003-0167-8123"},"institutions":[{"id":"https://openalex.org/I4210120689","display_name":"Universit\u00e4tsklinikum Aachen","ror":"https://ror.org/02gm5zw39","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210120689"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Birkholz","raw_affiliation_strings":["Department for Phoniatrics, Pedaudiology and Communication Disorders, University Hospital Aachen and RWTH Aachen University, Aachen, 52074, Germany","Department for Phoniatrics, Pedaudiology and Communication Disorders, University Hospital Aachen and RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department for Phoniatrics, Pedaudiology and Communication Disorders, University Hospital Aachen and RWTH Aachen University, Aachen, 52074, Germany","institution_ids":["https://openalex.org/I4210120689","https://openalex.org/I887968799"]},{"raw_affiliation_string":"Department for Phoniatrics, Pedaudiology and Communication Disorders, University Hospital Aachen and RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049702508","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0002-8541-2658"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Department of Speech, Hearing and Phonetic Sciences, University College London, London, WC1N 1PF, UK","Department of Speech Hearing and Phonetic Sciences University College London London UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Speech, Hearing and Phonetic Sciences, University College London, London, WC1N 1PF, UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Department of Speech Hearing and Phonetic Sciences University College London London UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003455071"],"corresponding_institution_ids":["https://openalex.org/I45129253","https://openalex.org/I60837268"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.9379,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.7856009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2014","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9987999796867371,"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/vocal-tract","display_name":"Vocal tract","score":0.9260650277137756},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7499969005584717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7041438221931458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6565234661102295},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5422220826148987},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4935826063156128},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4436684548854828},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3362257182598114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33430415391921997},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14389607310295105}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.9260650277137756},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7499969005584717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7041438221931458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6565234661102295},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5422220826148987},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4935826063156128},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4436684548854828},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3362257182598114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33430415391921997},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14389607310295105}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/1687-4722-2014-23","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-23","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-23","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1432133","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/1432133/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing , 2014 , Article 23. (2014)","raw_type":"Article"},{"id":"pmh:oai:publications.rwth-aachen.de:534428","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/534428","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on audio, speech, and music processing 2014(1), 23 (2014). doi:10.1186/1687-4722-2014-23","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2014-23","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2014-23","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2014-23","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123778414.pdf","grobid_xml":"https://content.openalex.org/works/W2123778414.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W46188241","https://openalex.org/W1508665513","https://openalex.org/W1570629387","https://openalex.org/W1587061027","https://openalex.org/W1875231349","https://openalex.org/W1891702304","https://openalex.org/W1944630683","https://openalex.org/W1965378753","https://openalex.org/W1966958746","https://openalex.org/W1969229349","https://openalex.org/W1970996882","https://openalex.org/W1977591085","https://openalex.org/W1980653762","https://openalex.org/W1986361563","https://openalex.org/W1991443301","https://openalex.org/W1995118599","https://openalex.org/W2011192906","https://openalex.org/W2025877346","https://openalex.org/W2026149420","https://openalex.org/W2043968544","https://openalex.org/W2044481232","https://openalex.org/W2048449762","https://openalex.org/W2058211894","https://openalex.org/W2063628328","https://openalex.org/W2069618035","https://openalex.org/W2085654611","https://openalex.org/W2088344125","https://openalex.org/W2110095567","https://openalex.org/W2123106640","https://openalex.org/W2126289105","https://openalex.org/W2135707066","https://openalex.org/W2141477623","https://openalex.org/W2141697795","https://openalex.org/W2143877646","https://openalex.org/W2154074091","https://openalex.org/W2155338111","https://openalex.org/W2396590251","https://openalex.org/W2396966646","https://openalex.org/W2596135543","https://openalex.org/W2596989490","https://openalex.org/W2604292070","https://openalex.org/W4253120335"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W1748856376","https://openalex.org/W4254341835","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2045900265","https://openalex.org/W2050311283"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,33,51,72,79,85,139,149,171,212],"estimation":[4],"of":[5,9,15,21,35,47,53,87,99,115,144,151,154],"underlying":[6],"articulatory":[7,64],"targets":[8],"Thai":[10,100,105,124,184,219],"vowels":[11,101,107,185,220],"as":[12,39,58,71,78,221,223],"invariant":[13],"representation":[14],"vocal":[16,127,140,176,213],"tract":[17,128,141,177,214],"shapes":[18,178,215],"by":[19,67,102,137],"means":[20],"analysis-by-synthesis":[22],"based":[23],"on":[24],"acoustic":[25,45],"data.":[26],"The":[27,161,174,193],"basic":[28],"idea":[29],"is":[30],"to":[31,95,132,147,168,182,207,216],"simulate":[32],"process":[34],"learning":[36,42],"speech":[37,91,112],"production":[38],"a":[40,62,90,122,133],"distal":[41],"task,":[43],"with":[44],"signals":[46],"natural":[48],"utterances":[49,118],"in":[50,108,187,190],"form":[52],"Mel-frequency":[54],"cepstral":[55],"coefficients":[56],"(MFCCs)":[57],"input,":[59],"VocalTractLab":[60],"-":[61],"3D":[63],"synthesizer":[65],"controlled":[66],"target":[68,80],"approximation":[69],"models":[70],"learner,":[73],"and":[74,158,189,197,209],"stochastic":[75,162],"gradient":[76,163],"descent":[77,164],"training":[81],"method.":[82],"To":[83],"test":[84],"effectiveness":[86],"this":[88,201],"approach,":[89],"corpus":[92,113],"was":[93,119,166],"designed":[94],"contain":[96],"contextual":[97],"variations":[98],"juxtaposing":[103],"nine":[104],"long":[106],"two-syllable":[109],"sequences.":[110,192],"A":[111],"consisting":[114],"81":[116],"disyllabic":[117,191],"recorded":[120],"from":[121],"native":[123],"speaker.":[125],"Nine":[126],"shapes,":[129],"each":[130,145],"corresponding":[131],"vowel,":[134],"were":[135,179],"estimated":[136],"optimizing":[138],"shape":[142,172],"parameters":[143],"vowel":[146],"minimize":[148],"sum":[150],"square":[152],"error":[153],"MFCCs":[155],"between":[156,227],"original":[157],"synthesized":[159],"speech.":[160],"algorithm":[165],"used":[167,181],"iteratively":[169],"optimize":[170],"parameters.":[173],"optimized":[175],"then":[180],"synthesize":[183,217],"both":[186,195],"monosyllables":[188],"results,":[194],"numerically":[196],"perceptually,":[198],"indicate":[199],"that":[200],"model-based":[202],"analysis":[203],"strategy":[204],"allows":[205],"us":[206],"effectively":[208],"economically":[210],"estimate":[211],"accurate":[218],"well":[222],"smooth":[224],"formant":[225],"transitions":[226],"adjacent":[228],"vowels.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}