{"id":"https://openalex.org/W2556218641","doi":"https://doi.org/10.1109/icsda.2014.7051442","title":"Estimating vocal tract shapes of Thai vowels from contextual vowel variation","display_name":"Estimating vocal tract shapes of Thai vowels from contextual vowel variation","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2556218641","doi":"https://doi.org/10.1109/icsda.2014.7051442","mag":"2556218641"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2014.7051442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/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":false,"raw_author_name":"Santitham Prom-on","raw_affiliation_strings":["Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Thailand","Department of Speech, University College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Mongkut's University of Technology Thonburi, Thailand","institution_ids":["https://openalex.org/I60837268"]},{"raw_affiliation_string":"Department of Speech, University College, London, United Kingdom","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/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Birkholz","raw_affiliation_strings":["Institute of Acoustics and Speech Communication, Technische Universit\u00e4t Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics and Speech Communication, Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"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, University College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Speech, University College, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.29934211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9995999932289124,"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":0.9994999766349792,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8776674866676331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7634698152542114},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7569942474365234},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6764017939567566},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6648727059364319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6493297815322876},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5603048205375671},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.44878390431404114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2901000380516052},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.1342434287071228}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8776674866676331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7634698152542114},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7569942474365234},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6764017939567566},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6648727059364319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6493297815322876},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5603048205375671},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.44878390431404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2901000380516052},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.1342434287071228},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsda.2014.7051442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10030728","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/10030728/","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":"In: (Proceedings) 17th Annual Conference of the Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA) / Conference on Asian Spoken Language Research and Evaluation (CASLRE). IEEE (2014)","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W46188241","https://openalex.org/W1875231349","https://openalex.org/W1891702304","https://openalex.org/W1944630683","https://openalex.org/W1965378753","https://openalex.org/W1969229349","https://openalex.org/W1977591085","https://openalex.org/W1980653762","https://openalex.org/W1991443301","https://openalex.org/W1995118599","https://openalex.org/W2002352051","https://openalex.org/W2025877346","https://openalex.org/W2026149420","https://openalex.org/W2048449762","https://openalex.org/W2053161809","https://openalex.org/W2058211894","https://openalex.org/W2063628328","https://openalex.org/W2069618035","https://openalex.org/W2088344125","https://openalex.org/W2110095567","https://openalex.org/W2126289105","https://openalex.org/W2141477623","https://openalex.org/W2143877646","https://openalex.org/W2154074091","https://openalex.org/W2396590251","https://openalex.org/W2396966646","https://openalex.org/W2596135543","https://openalex.org/W4253120335","https://openalex.org/W6639350448","https://openalex.org/W6735255722"],"related_works":["https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W2050311283","https://openalex.org/W2040757176","https://openalex.org/W3044927199","https://openalex.org/W2102353451","https://openalex.org/W2004149178","https://openalex.org/W1969107787","https://openalex.org/W2933771351","https://openalex.org/W14242463"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,52,111],"computational":[4],"estimation":[5],"of":[6,14,23,39,45,96,143],"vocal":[7],"tract":[8],"shape":[9,91],"parameters":[10,71],"as":[11,28],"articulatory":[12,19,106,141],"targets":[13,95,115,136],"Thai":[15,41,54,121,144],"vowels":[16,122],"in":[17,104,124,127],"an":[18],"synthesizer,":[20],"by":[21,51,67],"means":[22],"analysis-by-synthesis":[24,83],"with":[25],"acoustic":[26],"data":[27],"input.":[29],"A":[30],"speech":[31],"corpus":[32],"designed":[33],"to":[34,72,87,110,119],"capture":[35],"the":[36,69,74,90,134,139],"contextual":[37],"variants":[38],"nine":[40,105],"long":[42],"vowels,":[43],"consisting":[44],"81":[46],"disyllabic":[47,128],"utterances,":[48],"was":[49,85],"recorded":[50],"native":[53],"speaker.":[55],"For":[56],"each":[57,63,97,108],"utterance,":[58],"two":[59],"targets,":[60,107],"one":[61],"for":[62],"syllable,":[64],"were":[65,100,116],"estimated":[66,94,135],"optimizing":[68],"target":[70],"minimize":[73],"MFCC":[75],"error":[76],"between":[77],"original":[78],"and":[79,126],"synthesized":[80],"speech.":[81],"An":[82],"approach":[84],"used":[86,118],"iteratively":[88],"optimize":[89],"parameters.":[92],"The":[93,113,130],"vowel":[98],"type":[99],"then":[101,117],"averaged,":[102],"resulting":[103],"corresponding":[109],"vowel.":[112],"optimized":[114],"synthesize":[120],"both":[123],"monosyllables":[125],"sequences.":[129],"results":[131],"indicate":[132],"that":[133],"effectively":[137],"represent":[138],"underlying":[140],"goals":[142],"vowels.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}