{"id":"https://openalex.org/W4405633675","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800604","title":"Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID","display_name":"Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633675","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800604"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.19043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115563288","display_name":"Ahmad Alfani Handoyo","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Ahmad Alfani Handoyo","raw_affiliation_strings":["Bandung Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104156090","display_name":"Chung Tran","orcid":"https://orcid.org/0000-0003-1268-3630"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chung Tran","raw_affiliation_strings":["Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Puji Lestari","raw_affiliation_strings":["Bandung Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115563288"],"corresponding_institution_ids":["https://openalex.org/I134635517"],"apc_list":null,"apc_paid":null,"fwci":0.3407,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69345268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9937000274658203,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9912999868392944,"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/code-switching","display_name":"Code-switching","score":0.7923274040222168},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.6978641748428345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.679538905620575},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4773676097393036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46858495473861694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3659648299217224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27169081568717957}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7923274040222168},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.6978641748428345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679538905620575},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4773676097393036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46858495473861694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3659648299217224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27169081568717957},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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"},{"id":"pmh:oai:arXiv.org:2412.19043","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19043","pdf_url":"https://arxiv.org/pdf/2412.19043","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.19043","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19043","pdf_url":"https://arxiv.org/pdf/2412.19043","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1435354637","display_name":null,"funder_award_id":"JP23K21681","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2363020693","display_name":null,"funder_award_id":"21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3021549496","display_name":"Developing Low-Resource Multilingual Machine Speech Chain for Breaking Language Barriers","funder_award_id":"23K21681","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3670916553","display_name":null,"funder_award_id":"21H05","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8843746042","display_name":null,"funder_award_id":"JP21H0505","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338241","display_name":"Sakura Science Exchange Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405633675.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2911876655","https://openalex.org/W2963626623","https://openalex.org/W2964243274","https://openalex.org/W2983418531","https://openalex.org/W3008092184","https://openalex.org/W3015212790","https://openalex.org/W3025897121","https://openalex.org/W3030437843","https://openalex.org/W3033411150","https://openalex.org/W3196509775","https://openalex.org/W4200300291","https://openalex.org/W4200538527","https://openalex.org/W4381681023","https://openalex.org/W4385823293","https://openalex.org/W6775150526"],"related_works":["https://openalex.org/W4242621793","https://openalex.org/W648807974","https://openalex.org/W4229837155","https://openalex.org/W4236086937","https://openalex.org/W2294302573","https://openalex.org/W4312419881","https://openalex.org/W2086953810","https://openalex.org/W2512763533","https://openalex.org/W4248715694","https://openalex.org/W4281838804"],"abstract_inverted_index":{"Multilingual":[0],"text-to-speech":[1],"systems":[2],"convert":[3],"text":[4,13],"into":[5],"speech":[6,105],"across":[7],"multiple":[8],"languages.":[9,56],"In":[10],"many":[11],"cases,":[12],"sentences":[14],"may":[15],"contain":[16],"segments":[17],"in":[18,30,62],"different":[19],"languages,":[20],"a":[21,45,68],"phenomenon":[22],"known":[23],"as":[24,83,85],"code-switching.":[25],"This":[26,57],"is":[27],"particularly":[28],"common":[29],"Indonesia,":[31],"especially":[32],"between":[33,53],"Indonesian":[34,110],"and":[35,103,111],"English.":[36],"Despite":[37],"its":[38],"significance,":[39],"no":[40],"research":[41],"has":[42],"yet":[43],"developed":[44],"multilingual":[46],"TTS":[47],"system":[48],"capable":[49],"of":[50],"handling":[51],"code-switching":[52,61,98],"these":[54],"two":[55],"study":[58],"addresses":[59],"Indonesian-English":[60],"STEN-TTS.":[63],"Key":[64],"modifications":[65],"include":[66],"adding":[67],"language":[69,81,87],"identification":[70],"component":[71],"to":[72,108],"the":[73,90,97,109],"text-to-phoneme":[74],"conversion":[75],"using":[76],"finetuned":[77],"BERT":[78],"for":[79],"per-word":[80],"identification,":[82],"well":[84],"removing":[86],"embedding":[88],"from":[89],"base":[91],"model.":[92],"Experimental":[93],"results":[94],"demonstrate":[95],"that":[96],"model":[99],"achieves":[100],"superior":[101],"naturalness":[102],"improved":[104],"intelligibility":[106],"compared":[107],"English":[112],"baseline":[113],"STEN-TTS":[114],"models.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}