{"id":"https://openalex.org/W3011261571","doi":"https://doi.org/10.1109/o-cocosda46868.2019.9041195","title":"LOTUS-BI: A Thai-English Code-mixing Speech Corpus","display_name":"LOTUS-BI: A Thai-English Code-mixing Speech Corpus","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3011261571","doi":"https://doi.org/10.1109/o-cocosda46868.2019.9041195","mag":"3011261571"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda46868.2019.9041195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda46868.2019.9041195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-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/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":["Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002206098","display_name":"Vataya Chunwijitra","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":"Vataya Chunwijitra","raw_affiliation_strings":["Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083133506","display_name":"Phuttapong Sertsi","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":"Phuttapong Sertsi","raw_affiliation_strings":["Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091028151","display_name":"Patcharika Chootrakool","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":"Patcharika Chootrakool","raw_affiliation_strings":["Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083154069","display_name":"Sawit Kasuriya","orcid":"https://orcid.org/0000-0003-3429-0440"},"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":"Sawit Kasuriya","raw_affiliation_strings":["Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Text understanding Research Team, Artificial Intelligence Research Unit NECTEC, National Science and Technology Development Agency (NSTDA), 112 Phahonyothin Road, Khlong Neung, Khlong Luang, Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-mixing","display_name":"Code-mixing","score":0.7683224678039551},{"id":"https://openalex.org/keywords/lotus","display_name":"Lotus","score":0.6904544830322266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6788814663887024},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5194453597068787},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4480689465999603},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4263169467449188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3943207859992981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3903791606426239},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37245750427246094},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2355041205883026},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.1967240273952484},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08012020587921143},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07676523923873901},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06799432635307312},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.06171625852584839}],"concepts":[{"id":"https://openalex.org/C2778598016","wikidata":"https://www.wikidata.org/wiki/Q3201279","display_name":"Code-mixing","level":3,"score":0.7683224678039551},{"id":"https://openalex.org/C2777635637","wikidata":"https://www.wikidata.org/wiki/Q3645698","display_name":"Lotus","level":2,"score":0.6904544830322266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6788814663887024},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5194453597068787},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4480689465999603},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4263169467449188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3943207859992981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3903791606426239},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37245750427246094},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2355041205883026},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.1967240273952484},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08012020587921143},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07676523923873901},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06799432635307312},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.06171625852584839},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda46868.2019.9041195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda46868.2019.9041195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W99394049","https://openalex.org/W197277712","https://openalex.org/W880632652","https://openalex.org/W1545446185","https://openalex.org/W1583636673","https://openalex.org/W2007272231","https://openalex.org/W2061952799","https://openalex.org/W2089476159","https://openalex.org/W2251238585","https://openalex.org/W2340803683","https://openalex.org/W2346238792","https://openalex.org/W2807446620","https://openalex.org/W2944645009","https://openalex.org/W2982522484","https://openalex.org/W6691917203","https://openalex.org/W6704308951","https://openalex.org/W7043555223"],"related_works":["https://openalex.org/W2366835325","https://openalex.org/W2074679237","https://openalex.org/W4238472094","https://openalex.org/W162164374","https://openalex.org/W2922035700","https://openalex.org/W2461260704","https://openalex.org/W2348569083","https://openalex.org/W2384205838","https://openalex.org/W1960112736","https://openalex.org/W2800058963"],"abstract_inverted_index":{"Nowadays,":[0],"English":[1,171,190],"words":[2],"mixed":[3],"in":[4,10,61,128,179,186,192,197],"Thai":[5,144],"speech":[6,22,28,45,52,67,74,78,87,111,122],"are":[7,156,184],"usually":[8],"found":[9,185],"a":[11,25,42],"typical":[12],"speaking":[13],"style.":[14],"Consequently,":[15],"to":[16,48,63],"increase":[17],"the":[18,21,35,50,65,92,99,107,132,176,180,193,198],"performance":[19],"of":[20,39,89,109,124,135,150,158,170,175,188],"recognition":[23,68],"system,":[24],"Thai-English":[26,43],"code-mixing":[27,44,159],"corpus":[29,46,71,139,152,194],"is":[30,140,173],"required.":[31],"This":[32],"paper":[33],"describes":[34],"design":[36],"and":[37,58,83,95,104,164,195],"construction":[38],"LOTUS-BI":[40,70,138,151],"corpus:":[41],"aimed":[47],"be":[49],"essential":[51],"database":[53],"for":[54],"training":[55],"acoustic":[56],"model":[57,60],"language":[59],"order":[62],"obtain":[64],"better":[66],"accuracy.":[69],"contains":[72],"16.5":[73],"hours":[75,88,112,123],"from":[76,91,98,113,137],"4":[77],"tasks:":[79],"interview,":[80,93],"talk,":[81,94],"seminar,":[82],"meeting.":[84],"Now,":[85],"11.5":[86,121],"data":[90,125],"seminar":[96],"acquire":[97],"internet":[100],"have":[101],"been":[102,117],"transcribed":[103],"annotated.":[105],"Whereas,":[106],"rest":[108],"5":[110],"meeting":[114],"task":[115],"has":[116],"transcribing.":[118],"Therefore,":[119],"only":[120],"were":[126],"analyzed":[127],"this":[129],"paper.":[130],"Furthermore,":[131],"pronunciation":[133],"dictionary":[134],"vocabularies":[136,172,178,191],"created":[141],"based":[142],"on":[143],"phoneme":[145],"set.":[146],"The":[147,168],"statistical":[148],"analysis":[149],"revealed":[153],"that":[154],"there":[155],"37.96%":[157],"utterances,":[160],"including":[161],"34.23%":[162],"intra-sentential":[163],"3.73%":[165],"inter-sentential":[166],"utterances.":[167],"occurrence":[169],"29.04%":[174],"total":[177],"corpus.":[181],"Besides,":[182],"nouns":[183],"90%":[187],"all":[189],"10%":[196],"other":[199],"grammatical":[200],"categories.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}