{"id":"https://openalex.org/W1999860150","doi":"https://doi.org/10.1109/icsda.2013.6709907","title":"Towards language preservation: Design and collection of graphemically balanced and parallel speech corpora of Indonesian ethnic languages","display_name":"Towards language preservation: Design and collection of graphemically balanced and parallel speech corpora of Indonesian ethnic languages","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W1999860150","doi":"https://doi.org/10.1109/icsda.2013.6709907","mag":"1999860150"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2013.6709907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2013.6709907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","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/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":true,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Japan","Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Nara, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Nara, Japan#TAB#","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"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":"Satoshi Nakamura","raw_affiliation_strings":["Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Japan","Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Nara, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Augmented Human Communication Laboratory, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Nara, Japan#TAB#","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040108974"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.06755472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":0.9815000295639038,"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":0.9815000295639038,"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/T12031","display_name":"Speech and dialogue systems","score":0.9025999903678894,"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/indonesian","display_name":"Indonesian","score":0.9600328207015991},{"id":"https://openalex.org/keywords/indigenous","display_name":"Indigenous","score":0.7550130486488342},{"id":"https://openalex.org/keywords/ethnic-group","display_name":"Ethnic group","score":0.6241210103034973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6007541418075562},{"id":"https://openalex.org/keywords/languages-of-africa","display_name":"Languages of Africa","score":0.5979355573654175},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.592976450920105},{"id":"https://openalex.org/keywords/speech-community","display_name":"Speech community","score":0.5665732026100159},{"id":"https://openalex.org/keywords/indigenous-language","display_name":"Indigenous language","score":0.4408164322376251},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.3126554489135742},{"id":"https://openalex.org/keywords/anthropology","display_name":"Anthropology","score":0.18362078070640564}],"concepts":[{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.9600328207015991},{"id":"https://openalex.org/C55958113","wikidata":"https://www.wikidata.org/wiki/Q169480","display_name":"Indigenous","level":2,"score":0.7550130486488342},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.6241210103034973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007541418075562},{"id":"https://openalex.org/C108494575","wikidata":"https://www.wikidata.org/wiki/Q207930","display_name":"Languages of Africa","level":2,"score":0.5979355573654175},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.592976450920105},{"id":"https://openalex.org/C2779881370","wikidata":"https://www.wikidata.org/wiki/Q383340","display_name":"Speech community","level":2,"score":0.5665732026100159},{"id":"https://openalex.org/C2781370049","wikidata":"https://www.wikidata.org/wiki/Q645304","display_name":"Indigenous language","level":3,"score":0.4408164322376251},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3126554489135742},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.18362078070640564},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2013.6709907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2013.6709907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W46384587","https://openalex.org/W206967138","https://openalex.org/W746375014","https://openalex.org/W1500932846","https://openalex.org/W1987355695","https://openalex.org/W2153555222","https://openalex.org/W4250629472","https://openalex.org/W4402490932","https://openalex.org/W6601881065","https://openalex.org/W6629944598"],"related_works":["https://openalex.org/W3125673235","https://openalex.org/W3125101258","https://openalex.org/W203405652","https://openalex.org/W2261856492","https://openalex.org/W2068982449","https://openalex.org/W4297900994","https://openalex.org/W2160349241","https://openalex.org/W3213912220","https://openalex.org/W4214631250","https://openalex.org/W1999860150"],"abstract_inverted_index":{"Various":[0],"intangible":[1],"cultural":[2,31,82],"expressions":[3],"in":[4,55,68],"Indonesia":[5],"such":[6],"as":[7,43,45],"oral":[8],"traditions":[9],"and":[10,14,71,84,114,119,132],"literature":[11],"are":[12,22],"fragile":[13],"easily":[15],"lost.":[16],"Currently":[17],"among":[18,65],"726":[19],"languages,":[20,70],"146":[21],"endangered.":[23],"Although":[24],"several":[25],"projects":[26],"have":[27],"been":[28],"initiated":[29],"for":[30,76],"preservation,":[32],"the":[33,49,91],"available":[34],"technology":[35,61],"that":[36,62],"could":[37],"support":[38],"communication":[39,64],"within":[40],"indigenous":[41,77],"communities,":[42],"well":[44],"with":[46],"people":[47,66],"outside":[48],"community,":[50],"is":[51,59,74,111],"still":[52],"very":[53],"rare":[54],"Indonesia.":[56],"Speech-to-speech":[57],"translation":[58,99],"a":[60,112],"enables":[63],"speaking":[67],"different":[69],"therefore":[72],"it":[73],"significant":[75],"communities":[78],"to":[79,105],"preserve":[80],"their":[81],"language":[83,86],"overcome":[85],"barriers.":[87],"This":[88],"paper":[89],"presents":[90],"earlier":[92],"step":[93],"of":[94,97,116,123],"long-term":[95],"development":[96],"speech-to-speech":[98],"system":[100],"from":[101],"Indonesian":[102,125],"ethnic":[103,127],"languages":[104,107],"other":[106],"(i.e.,":[108],"English/Indonesian),":[109],"which":[110],"design":[113],"collection":[115],"graphemically":[117],"balanced":[118],"parallel":[120],"speech":[121],"corpora":[122],"four":[124],"major":[126],"languages:":[128],"Javanese,":[129],"Sundanese,":[130],"Balinese":[131],"Bataks.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}