{"id":"https://openalex.org/W2916997151","doi":"https://doi.org/10.1109/icassp.2019.8683745","title":"A Spelling Correction Model for End-to-end Speech Recognition","display_name":"A Spelling Correction Model for End-to-end Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2916997151","doi":"https://doi.org/10.1109/icassp.2019.8683745","mag":"2916997151"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5103232491","display_name":"Jinxi Guo","orcid":"https://orcid.org/0000-0001-9563-7351"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinxi Guo","raw_affiliation_strings":["University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.1689,"has_fulltext":false,"cited_by_count":142,"citation_normalized_percentile":{"value":0.98642199,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5651","last_page":"5655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8472880125045776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8123997449874878},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.8024241924285889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7040349245071411},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6616541147232056},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5776070356369019},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5553629398345947},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5293389558792114},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45872873067855835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43582484126091003},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4192585051059723},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3905784487724304},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24739226698875427},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08421853184700012}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8472880125045776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123997449874878},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8024241924285889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7040349245071411},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6616541147232056},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5776070356369019},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5553629398345947},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5293389558792114},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45872873067855835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43582484126091003},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4192585051059723},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3905784487724304},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24739226698875427},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08421853184700012},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1633171621","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2041670430","https://openalex.org/W2121879602","https://openalex.org/W2127141656","https://openalex.org/W2271840356","https://openalex.org/W2321916036","https://openalex.org/W2327501763","https://openalex.org/W2525778437","https://openalex.org/W2530876040","https://openalex.org/W2577366047","https://openalex.org/W2617258110","https://openalex.org/W2769810959","https://openalex.org/W2775304348","https://openalex.org/W2797303992","https://openalex.org/W2799800213","https://openalex.org/W2883586237","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963216553","https://openalex.org/W2963240019","https://openalex.org/W2963362078","https://openalex.org/W2963442512","https://openalex.org/W2963782041","https://openalex.org/W2964045208","https://openalex.org/W2964121744","https://openalex.org/W4294309260","https://openalex.org/W4294619240","https://openalex.org/W4327845728","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6694517276","https://openalex.org/W6700656258","https://openalex.org/W6743477263","https://openalex.org/W6752739165","https://openalex.org/W6753186555"],"related_works":["https://openalex.org/W3080136773","https://openalex.org/W2520160253","https://openalex.org/W2263232528","https://openalex.org/W4380605396","https://openalex.org/W2608712415","https://openalex.org/W2782005958","https://openalex.org/W4205868073","https://openalex.org/W4288754470","https://openalex.org/W3112480982","https://openalex.org/W4360942793"],"abstract_inverted_index":{"Attention-based":[0],"sequence-to-sequence":[1],"models":[2],"for":[3],"speech":[4],"recognition":[5],"jointly":[6],"train":[7],"an":[8,65,127,151,156],"acoustic":[9],"model,":[10],"language":[11,30],"model":[12,31,36,109,124,136],"(LM),":[13],"and":[14,22,143],"alignment":[15],"mechanism":[16],"using":[17,155],"a":[18,57,96,105,144],"single":[19],"neural":[20],"network":[21],"require":[23],"only":[24,38],"parallel":[25],"audio-text":[26,42],"pairs.":[27],"Thus,":[28],"the":[29,34,73,83,89,116,122,134],"component":[32],"of":[33,59,77],"end-to-end":[35,74],"is":[37],"trained":[39,68],"on":[40,50,69],"transcribed":[41],"pairs,":[43],"which":[44],"leads":[45],"to":[46,99,110],"performance":[47],"degradation":[48],"especially":[49],"rare":[51],"words.":[52],"While":[53],"there":[54],"have":[55,79],"been":[56],"variety":[58],"work":[60],"that":[61,121],"look":[62],"at":[63],"incorporating":[64],"external":[66,157],"LM":[67],"text-only":[70,101],"data":[71],"into":[72,81],"framework,":[75],"none":[76],"them":[78],"taken":[80],"account":[82],"characteristic":[84],"error":[85],"distribution":[86],"made":[87],"by":[88,103],"model.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94,119],"propose":[95],"novel":[97],"approach":[98],"utilizing":[100],"data,":[102],"training":[104],"spelling":[106],"correction":[107],"(SC)":[108],"explicitly":[111],"correct":[112],"those":[113],"errors.":[114],"On":[115],"LibriSpeech":[117],"dataset,":[118],"demonstrate":[120],"proposed":[123],"results":[125],"in":[126,131],"18.6%":[128],"relative":[129,146],"improvement":[130,147],"WER":[132],"over":[133],"baseline":[135],"when":[137,148],"directly":[138],"correcting":[139],"top":[140],"ASR":[141],"hypothesis,":[142],"29.0%":[145],"further":[149],"rescoring":[150],"expanded":[152],"n-best":[153],"list":[154],"LM.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}