{"id":"https://openalex.org/W3181014475","doi":"https://doi.org/10.21437/interspeech.2021-1040","title":"kosp2e: Korean Speech to English Translation Corpus","display_name":"kosp2e: Korean Speech to English Translation Corpus","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3181014475","doi":"https://doi.org/10.21437/interspeech.2021-1040","mag":"3181014475"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1040","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.02875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102984975","display_name":"Won Ik Cho","orcid":"https://orcid.org/0000-0002-8882-9125"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Ik Cho","raw_affiliation_strings":["Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086508893","display_name":"Seok\u2010min Kim","orcid":"https://orcid.org/0000-0002-1609-6786"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seok Min Kim","raw_affiliation_strings":["Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003905071","display_name":"Hyunchang Cho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunchang Cho","raw_affiliation_strings":["NAVER CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09155746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3705","last_page":"3709"},"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/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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8409891724586487},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7745875120162964},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7392930388450623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.676619291305542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6143964529037476},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.5551038980484009},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4824810326099396},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45073428750038147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42815354466438293},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.41134777665138245},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.39980548620224},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2811114192008972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409891724586487},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7745875120162964},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7392930388450623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.676619291305542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6143964529037476},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5551038980484009},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4824810326099396},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45073428750038147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42815354466438293},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41134777665138245},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.39980548620224},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2811114192008972},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1040","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.02875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.02875","pdf_url":"https://arxiv.org/pdf/2107.02875","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3181014475","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2107.02875.pdf","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:s-space.snu.ac.kr:10371/186864","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/186864","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.2107.02875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.02875","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.02875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.02875","pdf_url":"https://arxiv.org/pdf/2107.02875","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3181014475.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1982867762","https://openalex.org/W2101105183","https://openalex.org/W2740107491","https://openalex.org/W2785350307","https://openalex.org/W2933138175","https://openalex.org/W2945700568","https://openalex.org/W2949328740","https://openalex.org/W2955541912","https://openalex.org/W2963403868","https://openalex.org/W2963532001","https://openalex.org/W2964104866","https://openalex.org/W2972448360","https://openalex.org/W3045622142","https://openalex.org/W3096490862","https://openalex.org/W3100129654","https://openalex.org/W3118578889","https://openalex.org/W3136663470"],"related_works":["https://openalex.org/W3197233518","https://openalex.org/W3043665049","https://openalex.org/W3054645415","https://openalex.org/W3004753145","https://openalex.org/W3092085609","https://openalex.org/W3111143273","https://openalex.org/W2756675017","https://openalex.org/W2884066185","https://openalex.org/W2758724354","https://openalex.org/W2407051582","https://openalex.org/W3183419084","https://openalex.org/W2172066455","https://openalex.org/W2541718661","https://openalex.org/W2250876691","https://openalex.org/W3120112486","https://openalex.org/W2963697731","https://openalex.org/W2250262549","https://openalex.org/W2762715843","https://openalex.org/W2091957306","https://openalex.org/W3173842124"],"abstract_inverted_index":{"Most":[0],"speech-to-text":[1],"(S2T)":[2],"translation":[3,84],"studies":[4],"use":[5],"English":[6,40,71,129],"speech":[7,66,81],"as":[8,59],"a":[9,61],"source,":[10],"which":[11],"makes":[12],"it":[13],"difficult":[14],"for":[15,124,142],"non-English":[16],"speakers":[17],"to":[18,67,90,96,139],"take":[19],"advantage":[20],"of":[21,120,134],"the":[22,36,42,97,101,104,117,128,132,150],"S2T":[23],"technologies.":[24],"For":[25],"some":[26],"languages,":[27],"this":[28,45,53],"problem":[29],"was":[30],"tackled":[31],"through":[32,103,146],"corpus":[33,62],"construction,":[34],"but":[35],"farther":[37],"linguistically":[38],"from":[39],"or":[41],"more":[43,50],"under-resourced,":[44],"deficiency":[46],"and":[47,86,99,106,111,122],"underrepresentedness":[48],"becomes":[49],"significant.":[51],"In":[52],"paper,":[54],"we":[55,115],"introduce":[56],"kosp2e":[57],"(read":[58],"`kospi'),":[60],"that":[63],"allows":[64],"Korean":[65],"be":[68],"translated":[69],"into":[70],"text":[72],"in":[73,149],"an":[74],"end-to-end":[75,113],"manner.":[76],"We":[77,137],"adopt":[78],"open":[79],"license":[80],"recognition":[82],"corpus,":[83,85],"spoken":[87],"language":[88],"corpora":[89],"make":[91],"our":[92,135],"dataset":[93],"freely":[94],"available":[95],"public,":[98],"check":[100],"performance":[102],"pipeline":[105,110],"training-based":[107],"approaches.":[108],"Using":[109],"various":[112],"schemes,":[114],"obtain":[116],"highest":[118],"BLEU":[119],"21.3":[121],"18.0":[123],"each":[125],"based":[126],"on":[127],"hypothesis,":[130],"validating":[131],"feasibility":[133],"data.":[136],"plan":[138],"supplement":[140],"annotations":[141],"other":[143],"target":[144],"languages":[145],"community":[147],"contributions":[148],"future.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}