{"id":"https://openalex.org/W2921000669","doi":"https://doi.org/10.23919/apsipa.2018.8659735","title":"Low-Frequency Character Clustering for End-to-End ASR System","display_name":"Low-Frequency Character Clustering for End-to-End ASR System","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921000669","doi":"https://doi.org/10.23919/apsipa.2018.8659735","mag":"2921000669"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659735","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5111505711","display_name":"Hitoshi Ito","orcid":"https://orcid.org/0009-0007-9155-2386"},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hitoshi Ito","raw_affiliation_strings":["NHK (Japan Broadcasting Corp.), Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corp.), Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027308668","display_name":"Aiko Hagiwara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aiko Hagiwara","raw_affiliation_strings":["NHK (Japan Broadcasting Corp.), Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corp.), Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090880731","display_name":"Manon Ichiki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Manon Ichiki","raw_affiliation_strings":["NHK (Japan Broadcasting Corp.), Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corp.), Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042879882","display_name":"Takeshi Kobayakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Kobayakawa","raw_affiliation_strings":["NHK (Japan Broadcasting Corp.), Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corp.), Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Takeshi Mishima","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Mishima","raw_affiliation_strings":["NHK (Japan Broadcasting Corp.), Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corp.), Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109470000","display_name":"Shoei Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107548","display_name":"Japan Broadcasting Corporation (Japan)","ror":"https://ror.org/01s8tz949","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210107548"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoei Sato","raw_affiliation_strings":["NHK (Japan Broadcasting Corp.), Japan"],"affiliations":[{"raw_affiliation_string":"NHK (Japan Broadcasting Corp.), Japan","institution_ids":["https://openalex.org/I4210107548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079042022","display_name":"Akio Kobayashi","orcid":"https://orcid.org/0000-0002-6927-7353"},"institutions":[{"id":"https://openalex.org/I24254649","display_name":"Tsukuba University of Technology","ror":"https://ror.org/057bx9y85","country_code":"JP","type":"education","lineage":["https://openalex.org/I24254649"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akio Kobayashi","raw_affiliation_strings":["Tsukuba University of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tsukuba University of Technology, Japan","institution_ids":["https://openalex.org/I24254649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111505711"],"corresponding_institution_ids":["https://openalex.org/I4210107548"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19019982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7917124032974243},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6826233267784119},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6069961190223694},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6033335328102112},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5912086367607117},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5901565551757812},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5516027212142944},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5245388150215149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5108892321586609},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49214237928390503},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4916093945503235},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4791014492511749},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46465176343917847},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44956159591674805},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34101009368896484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08336380124092102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917124032974243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6826233267784119},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6069961190223694},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6033335328102112},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5912086367607117},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5901565551757812},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5516027212142944},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5245388150215149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5108892321586609},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49214237928390503},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4916093945503235},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4791014492511749},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46465176343917847},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44956159591674805},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34101009368896484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08336380124092102},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659735","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1533416326","https://openalex.org/W1922655562","https://openalex.org/W2046932483","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2158069733","https://openalex.org/W2193413348","https://openalex.org/W2293858598","https://openalex.org/W2402146185","https://openalex.org/W2512608784","https://openalex.org/W2515801922","https://openalex.org/W2530486890","https://openalex.org/W2594856242","https://openalex.org/W2597757402","https://openalex.org/W2627092829","https://openalex.org/W2785450052","https://openalex.org/W2952288254","https://openalex.org/W2963211739","https://openalex.org/W2963953073","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W2916997151","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424"],"abstract_inverted_index":{"We":[0,109],"developed":[1],"a":[2,38,60,100,115,141,147],"label-designing":[3],"and":[4,105,151],"restoration":[5],"method":[6,69,113,139,150],"for":[7],"end-to-end":[8,20,117],"automatic":[9,118],"speech":[10],"recognition":[11],"based":[12],"on":[13],"connectionist":[14],"temporal":[15],"classification":[16],"(CTC).":[17],"With":[18,45],"an":[19],"speech-recognition":[21,119],"system":[22,120],"including":[23,121],"thousands":[24,84],"of":[25,42,59,83,85,123,143],"output":[26],"labels":[27,81,91,97,122],"such":[28],"as":[29],"words":[30],"or":[31],"characters,":[32],"it":[33],"is":[34,152],"difficult":[35],"to":[36,94,114,154],"train":[37,75],"robust":[39],"model":[40,62],"because":[41],"data":[43,53],"sparsity.":[44],"our":[46,138],"proposed":[47,112],"method,":[48],"characters":[49],"with":[50,137,146],"less":[51],"training":[52],"are":[54,92],"estimated":[55],"using":[56,78,99],"the":[57,65,89,95,111,131],"context":[58],"language":[61,107],"rather":[63],"than":[64],"acoustic":[66,76],"features.":[67],"Our":[68],"involves":[70],"two":[71],"steps.":[72],"First,":[73],"we":[74],"models":[77],"70":[79],"class":[80,90],"instead":[82],"low-frequency":[86],"labels.":[87],"Second,":[88],"restored":[93],"original":[96],"by":[98,140],"weighted":[101],"finite":[102],"state":[103],"transducer":[104],"n-gram":[106],"model.":[108],"applied":[110],"Japanese":[116],"over":[124],"3,000":[125],"characters.":[126],"Experimental":[127],"results":[128],"indicate":[129],"that":[130],"word":[132],"error":[133],"rate":[134],"relatively":[135],"improved":[136],"maximum":[142],"15.5%":[144],"compared":[145],"conventional":[148],"CTC-based":[149],"comparable":[153],"state-of-the-art":[155],"hybrid":[156],"DNN":[157],"methods.":[158]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}