{"id":"https://openalex.org/W1521340514","doi":"https://doi.org/10.21437/icslp.1998-683","title":"The design of the newspaper-based Japanese large vocabulary continuous speech recognition corpus","display_name":"The design of the newspaper-based Japanese large vocabulary continuous speech recognition corpus","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W1521340514","doi":"https://doi.org/10.21437/icslp.1998-683","mag":"1521340514"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-683","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4671","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108574981","display_name":"Katunobu Itou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Katunobu Itou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112451327","display_name":"Mikio Yamamoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikio Yamamoto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037962051","display_name":"Toshiyuki Takezawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshiyuki Takezawa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109273395","display_name":"Tatsuo Matsuoka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuo Matsuoka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyohiro Shikano","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111539599","display_name":"Shuichi Itahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuichi Itahashi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5108574981"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2955,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.92215696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"paper 0722","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9470999836921692,"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":0.9470999836921692,"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":0.9128999710083008,"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/newspaper","display_name":"Newspaper","score":0.7777512073516846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548387050628662},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7391001582145691},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6939924955368042},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5693176984786987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4759927988052368},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4398077428340912},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24384886026382446},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.20654138922691345},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.04581153392791748}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7777512073516846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548387050628662},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7391001582145691},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6939924955368042},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5693176984786987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4759927988052368},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4398077428340912},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24384886026382446},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.20654138922691345},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.04581153392791748},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.1998-683","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783122","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4671","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783122","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4671","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W160213850","https://openalex.org/W1521741510","https://openalex.org/W2144158482","https://openalex.org/W2153073500","https://openalex.org/W2528382923"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W2100945520","https://openalex.org/W2386525189","https://openalex.org/W2360284199","https://openalex.org/W2620505790"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,20],"present":[4],"the":[5,35,39,67],"first":[6],"public":[7],"Japanese":[8],"speech":[9,15,48],"corpus":[10,46,76],"for":[11,56],"large":[12],"vocabulary":[13],"continuous":[14],"recognition":[16],"(LVCSR)":[17],"technology,":[18],"which":[19],"have":[21],"titled":[22],"JNAS":[23,93],"(Japanese":[24],"Newspaper":[25],"Article":[26],"Sentences).":[27],"We":[28],"designed":[29],"it":[30],"to":[31,34],"be":[32],"comparable":[33],"corpora":[36],"used":[37],"in":[38],"American":[40],"and":[41,52,61,70],"European":[42],"LVCSR":[43],"projects.":[44],"The":[45],"contains":[47,77],"recordings":[49],"(60":[50],"hrs.)":[51],"their":[53],"orthographic":[54],"transcriptions":[55],"306":[57],"speakers":[58],"(153":[59],"males":[60],"153":[62],"females)":[63],"reading":[64,89],"excerpts":[65],"from":[66],"newspaper's":[68],"articles":[69],"phonetically":[71],"balanced":[72],"(PB)":[73],"sentences.":[74,92],"This":[75],"utterances":[78],"of":[79],"about":[80,90],"45,000":[81],"sentences":[82],"as":[83],"a":[84],"whole":[85],"with":[86],"each":[87],"speaker":[88],"150":[91],"is":[94],"being":[95],"distributed":[96],"on":[97],"16":[98],"CD-ROMs.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
