{"id":"https://openalex.org/W3016250025","doi":"https://doi.org/10.1109/icassp40776.2020.9053226","title":"Converting Written Language to Spoken Language with Neural Machine Translation for Language Modeling","display_name":"Converting Written Language to Spoken Language with Neural Machine Translation for Language Modeling","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016250025","doi":"https://doi.org/10.1109/icassp40776.2020.9053226","mag":"3016250025"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103585099","display_name":"Shintaro Ando","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shintaro Ando","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering","Graduate School of Engineering, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028857766","display_name":"Nobuyasu Itoh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyasu Itoh","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering","Graduate School of Engineering, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103585099"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51722441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"83","issue":null,"first_page":"8124","last_page":"8128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.870472252368927},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8018524646759033},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6661929488182068},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6421040296554565},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.629056990146637},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6211127638816833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6209294199943542},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5717341303825378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5191361308097839},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45554298162460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870472252368927},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8018524646759033},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6661929488182068},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6421040296554565},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.629056990146637},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6211127638816833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6209294199943542},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5717341303825378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5191361308097839},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45554298162460327},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W258837700","https://openalex.org/W2097927681","https://openalex.org/W2097931979","https://openalex.org/W2105830342","https://openalex.org/W2116047093","https://openalex.org/W2118607665","https://openalex.org/W2148573886","https://openalex.org/W2398591941","https://openalex.org/W2562183142","https://openalex.org/W2583741591","https://openalex.org/W2747236259","https://openalex.org/W2890144771","https://openalex.org/W2938704169","https://openalex.org/W2939021222","https://openalex.org/W2946375144","https://openalex.org/W2949555952","https://openalex.org/W2963096510","https://openalex.org/W2963403868","https://openalex.org/W2963979492","https://openalex.org/W2971167892","https://openalex.org/W2996287690","https://openalex.org/W4230792866","https://openalex.org/W4385245566","https://openalex.org/W6712946189","https://openalex.org/W6728274705","https://openalex.org/W6730845088","https://openalex.org/W6733384274","https://openalex.org/W6739901393","https://openalex.org/W6761551260","https://openalex.org/W6762471145"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W3151736118","https://openalex.org/W2279116787","https://openalex.org/W2404510748","https://openalex.org/W3089218859","https://openalex.org/W2034361844","https://openalex.org/W2003020325","https://openalex.org/W2164499211"],"abstract_inverted_index":{"When":[0],"building":[1],"a":[2,15,48,70,85,114],"language":[3,40,45],"model":[4,106],"(LM)":[5],"for":[6,99,127],"spontaneous":[7,60],"speech,":[8],"the":[9,75,104,122,141],"ideal":[10],"situation":[11],"is":[12,28,107],"to":[13,73,95,117],"have":[14],"large":[16,86],"amount":[17],"of":[18,58,88,90,109,136],"spoken,":[19],"in-domain":[20],"training":[21,128],"data.":[22],"Having":[23],"such":[24],"abundant":[25],"data,":[26],"however,":[27],"not":[29],"realistic.":[30],"We":[31,54,78,101],"address":[32],"this":[33],"problem":[34],"by":[35,46],"generating":[36],"texts":[37,89,112,124],"in":[38,43,113],"spoken":[39,118],"from":[41],"those":[42],"written":[44,64,111],"using":[47],"neural":[49],"machine":[50],"translation":[51],"(NMT)":[52],"model.":[53,77],"collected":[55],"faithful":[56],"transcripts":[57],"fully":[59],"speech":[61,137],"and":[62,66,120],"corresponding":[63],"versions":[65],"used":[67,79],"them":[68],"as":[69,93],"parallel":[71],"corpus":[72],"train":[74],"NMT":[76,105],"top-k":[80],"random":[81],"sampling,":[82],"which":[83],"generates":[84],"variety":[87],"higher":[91],"quality":[92],"compared":[94],"other":[96],"generation":[97],"methods":[98],"NMT.":[100],"indicate":[102],"that":[103,121],"capable":[108],"converting":[110],"certain":[115],"domain":[116],"texts,":[119],"converted":[123],"are":[125],"effective":[126],"LMs.":[129,142],"Our":[130],"experimental":[131],"results":[132],"show":[133],"significant":[134],"improvement":[135],"recognition":[138],"accuracy":[139],"with":[140]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}