{"id":"https://openalex.org/W2808226167","doi":"https://doi.org/10.1109/icsda.2017.8384421","title":"ConPro: Heteronym pronunciation corpus with context information for text-to-phoneme evaluation in Thai","display_name":"ConPro: Heteronym pronunciation corpus with context information for text-to-phoneme evaluation in Thai","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2808226167","doi":"https://doi.org/10.1109/icsda.2017.8384421","mag":"2808226167"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","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/A5029765234","display_name":"Chatchawarn Hansakunbuntheung","orcid":"https://orcid.org/0000-0003-4064-4882"},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Chatchawarn Hansakunbuntheung","raw_affiliation_strings":["National Science and Technology Development Agency (NSTDA), National Electronics and Computer Technology Center (NECTEC), Pathumthani, Thailand"],"affiliations":[{"raw_affiliation_string":"National Science and Technology Development Agency (NSTDA), National Electronics and Computer Technology Center (NECTEC), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029790262","display_name":"Sumonmas Thatphithakkul","orcid":null},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Sumonmas Thatphithakkul","raw_affiliation_strings":["National Science and Technology Development Agency (NSTDA), National Electronics and Computer Technology Center (NECTEC), Pathumthani, Thailand"],"affiliations":[{"raw_affiliation_string":"National Science and Technology Development Agency (NSTDA), National Electronics and Computer Technology Center (NECTEC), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029765234"],"corresponding_institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23343391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.995199978351593,"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/T13629","display_name":"Text Readability and Simplification","score":0.9865000247955322,"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":0.8885443210601807},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332913517951965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7283405065536499},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.6866672039031982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6305453777313232},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6281229853630066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5363598465919495},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43495744466781616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3369056284427643},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08489242196083069}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8885443210601807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332913517951965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7283405065536499},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.6866672039031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305453777313232},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6281229853630066},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5363598465919495},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43495744466781616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3369056284427643},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08489242196083069},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2017.8384421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W108353034","https://openalex.org/W202122741","https://openalex.org/W1589180892","https://openalex.org/W1989026251","https://openalex.org/W2018061374","https://openalex.org/W2101876785","https://openalex.org/W2103221037","https://openalex.org/W2133834138","https://openalex.org/W2220291064","https://openalex.org/W6608125908","https://openalex.org/W6680092363"],"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/W2359469050","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Heteronyms,":[0],"which":[1],"are":[2,27],"texts":[3,105],"with":[4,47,72],"multiple":[5,48],"pronunciations":[6],"depending":[7],"on":[8],"their":[9],"contexts,":[10],"is":[11,52],"a":[12,65],"crucial":[13],"problem":[14,125],"in":[15,36,127],"text-to-":[16],"phoneme":[17],"conversion.":[18],"Conventional":[19],"pronunciation":[20,67],"corpora":[21],"that":[22],"collect":[23],"only":[24],"grapheme-phoneme":[25],"pairs":[26],"not":[28],"enough":[29],"to":[30],"evaluate":[31],"the":[32,42,80,88,97,138],"heteronym":[33,134],"issue.":[34],"Furthermore,":[35],"no-word-":[37],"break":[38],"languages":[39],"e.g.":[40],"Thai,":[41],"issue":[43],"of":[44,56,69,82,87,120,140],"orthographic":[45,94,115,121],"groups":[46],"possible":[49],"word":[50],"segmentation":[51],"another":[53],"major":[54],"cause":[55],"ambiguous":[57],"pronunciations.":[58],"Thus,":[59],"this":[60],"paper":[61],"proposes":[62],"\"ConPro\"":[63],"corpus,":[64],"context-dependent":[66],"corpus":[68,89],"Thai":[70],"heteronyms":[71,141],"systematic":[73],"collection":[74],"and":[75,102,117,142],"context":[76],"information":[77],"for":[78,113,136],"evaluating":[79,107],"accuracy":[81],"text-to-phoneme":[83,128],"conversions.":[84],"The":[85],"keys":[86],"design":[90],"include":[91],"1)":[92],"multiple-word":[93],"group":[95],"as":[96,106],"basic":[98],"unit,":[99],"2)":[100],"pragmatic":[101],"compact":[103],"contextual":[104],"texts,":[108],"3)":[109],"Categorial":[110],"Matrix":[111],"tags":[112],"representing":[114],"types":[116],"usage":[118],"domains":[119],"groups,":[122],"and,":[123,130],"investigating":[124],"categories":[126],"conversions,":[129],"4)":[131],"pronunciation-and-":[132],"meaning-prioritized":[133],"collecting":[135],"extending":[137],"coverage":[139],"contexts.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}