{"id":"https://openalex.org/W2148182949","doi":"https://doi.org/10.1109/icassp.2011.5947623","title":"Training of error-corrective model for ASR without using audio data","display_name":"Training of error-corrective model for ASR without using audio data","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2148182949","doi":"https://doi.org/10.1109/icassp.2011.5947623","mag":"2148182949"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research Tokyo, Yamato, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028857766","display_name":"Nobuyasu Itoh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuyasu Itoh","raw_affiliation_strings":["IBM Research Tokyo, Yamato, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083574298","display_name":"Masafumi Nishimura","orcid":"https://orcid.org/0000-0001-7633-9340"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masafumi Nishimura","raw_affiliation_strings":["IBM Research Tokyo, Yamato, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Tokyo, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5576","last_page":"5579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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/discriminative-model","display_name":"Discriminative model","score":0.8531136512756348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8304342031478882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8002617359161377},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5631344318389893},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5289385914802551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4740821123123169},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4689972400665283},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4073103964328766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38303014636039734}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8531136512756348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304342031478882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8002617359161377},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5631344318389893},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5289385914802551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4740821123123169},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4689972400665283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4073103964328766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38303014636039734},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W99561634","https://openalex.org/W168280322","https://openalex.org/W181494806","https://openalex.org/W202240798","https://openalex.org/W2005076803","https://openalex.org/W2008652694","https://openalex.org/W2019191646","https://openalex.org/W2040870580","https://openalex.org/W2046932483","https://openalex.org/W2096938374","https://openalex.org/W2113687551","https://openalex.org/W2122537498","https://openalex.org/W2128661689","https://openalex.org/W2137675115","https://openalex.org/W2156804424","https://openalex.org/W2158025800","https://openalex.org/W2158195707","https://openalex.org/W2165835488","https://openalex.org/W2166799778","https://openalex.org/W6607432625","https://openalex.org/W6651845459","https://openalex.org/W6677161487","https://openalex.org/W6678797682","https://openalex.org/W6684416082"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W3172695526"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3],"method":[4],"to":[5],"train":[6],"an":[7],"error-corrective":[8,93],"model":[9,94],"for":[10],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR)":[14],"without":[15],"using":[16],"audio":[17,27,47],"data.":[18,48],"In":[19],"existing":[20],"techniques,":[21],"it":[22],"is":[23,34,52],"assumed":[24],"that":[25,120],"sufficient":[26],"data":[28,71,99,118],"of":[29,72,130],"the":[30,63,69,73,92,97,104,108,125,128,131],"tar":[31],"get":[32],"application":[33,75],"available":[35],"and":[36,103],"negative":[37,111],"samples":[38,102],"can":[39],"be":[40],"prepared":[41],"by":[42,76,95],"having":[43],"ASR":[44,64],"recognize":[45],"this":[46,50,84],"However,":[49],"assumption":[51],"not":[53],"always":[54],"true.":[55],"We":[56,82,87],"propose":[57],"generating":[58],"probable":[59],"N-best":[60,105],"lists,":[61],"which":[62],"may":[65],"produce,":[66],"directly":[67],"from":[68,107],"text":[70,98],"target":[74],"taking":[77],"phoneme":[78],"similarity":[79],"into":[80],"consideration.":[81],"call":[83,116],"process":[85],"\"Pseudo-ASR\".":[86],"conduct":[88],"discriminative":[89,121],"reranking":[90,122],"with":[91,114],"regarding":[96],"as":[100,110],"positive":[101],"lists":[106],"Pseudo-ASR":[109,126],"samples.":[112],"Experiments":[113],"Japanese":[115],"center":[117],"showed":[119],"based":[123],"on":[124],"improved":[127],"accuracy":[129],"ASR.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}