{"id":"https://openalex.org/W4221165942","doi":"https://doi.org/10.1109/taslp.2022.3205753","title":"Towards Contextual Spelling Correction for Customization of End-to-End Speech Recognition Systems","display_name":"Towards Contextual Spelling Correction for Customization of End-to-End Speech Recognition Systems","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4221165942","doi":"https://doi.org/10.1109/taslp.2022.3205753"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3205753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3205753","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5103233401","display_name":"Xiaoqiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoqiang Wang","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360935","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0003-0412-8805"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqing Liu","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090622608","display_name":"Veljko Miljanic","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Veljko Miljanic","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104034889","display_name":"Hosam Khalil","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hosam Khalil","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103233401"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.2525,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89435794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"3089","last_page":"3097"},"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":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.7922568321228027},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6507421135902405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6151083707809448},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.602843165397644},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5094032883644104},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5064901113510132},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.4952780306339264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49173620343208313},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.45512861013412476},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4283865988254547},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41876330971717834},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1320337951183319},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0830337405204773},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08044436573982239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922568321228027},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6507421135902405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6151083707809448},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.602843165397644},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5094032883644104},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5064901113510132},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.4952780306339264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49173620343208313},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.45512861013412476},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4283865988254547},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41876330971717834},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1320337951183319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0830337405204773},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08044436573982239},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3205753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3205753","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2020278455","https://openalex.org/W2105482032","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2916997151","https://openalex.org/W2937402758","https://openalex.org/W2962760690","https://openalex.org/W2972625221","https://openalex.org/W2972650231","https://openalex.org/W3007227084","https://openalex.org/W3011339933","https://openalex.org/W3011594683","https://openalex.org/W3015190365","https://openalex.org/W3015194534","https://openalex.org/W3015752032","https://openalex.org/W3016010032","https://openalex.org/W3028545098","https://openalex.org/W3028709955","https://openalex.org/W3094667432","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3161873870","https://openalex.org/W3193959417","https://openalex.org/W3198004110","https://openalex.org/W3205495812","https://openalex.org/W3211278025","https://openalex.org/W4224919446","https://openalex.org/W4226292626","https://openalex.org/W4226462878","https://openalex.org/W4288088457","https://openalex.org/W4292025450","https://openalex.org/W4395957972","https://openalex.org/W6638523607","https://openalex.org/W6679436768","https://openalex.org/W6739901393","https://openalex.org/W6769806307","https://openalex.org/W6780226713","https://openalex.org/W6794876948"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2021532426","https://openalex.org/W2081317458"],"abstract_inverted_index":{"Contextual":[0],"biasing":[1,23,46,66,125,136,171],"is":[2,133,139],"an":[3],"important":[4],"and":[5,47,105,118,141,168,186],"challenging":[6],"task":[7],"for":[8],"end-to-end":[9,52,78],"automatic":[10],"speech":[11],"recognition":[12,20],"(ASR)":[13],"systems,":[14],"which":[15,138],"aims":[16],"to":[17,27,63,113,122,174],"achieve":[18],"better":[19],"performance":[21,119],"by":[22,67,184,190],"the":[24,77,124,128,151,175,178],"ASR":[25,53,79,166],"system":[26,167],"particular":[28],"context":[29,94,116],"phrases":[30],"such":[31],"as":[32,155,157],"person":[33],"names,":[34],"music":[35],"list,":[36],"proper":[37],"nouns,":[38],"etc.":[39],"Existing":[40],"methods":[41],"mainly":[42],"include":[43],"contextual":[44,65,70,83],"LM":[45],"adding":[48,68],"bias":[49],"encoder":[50],"into":[51,85],"models.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"introduce":[59],"a":[60,69,86,92,134],"novel":[61],"approach":[62],"do":[64],"spelling":[71,88],"correction":[72,89],"model":[73,90,98,132,180,182],"on":[74],"top":[75],"of":[76,127],"system.":[80],"We":[81,108],"incorporate":[82],"information":[84],"sequence-to-sequence":[87],"with":[91],"shared":[93],"encoder.":[95],"The":[96,130],"proposed":[97,131,152],"includes":[99],"two":[100],"different":[101,146],"mechanisms:":[102],"autoregressive":[103],"(AR)":[104],"non-autoregressive":[106],"(NAR).":[107],"also":[109],"propose":[110],"filtering":[111],"algorithms":[112],"handle":[114],"large-size":[115],"lists,":[117],"balancing":[120],"mechanisms":[121],"control":[123],"degree":[126],"model.":[129],"general":[135],"solution":[137],"domain-insensitive":[140],"can":[142],"be":[143],"adopted":[144],"in":[145],"scenarios.":[147],"Experiments":[148],"show":[149],"that":[150],"method":[153],"achieves":[154],"much":[156],"51%":[158],"relative":[159],"word":[160],"error":[161],"rate":[162],"(WER)":[163],"reduction":[164],"over":[165],"outperforms":[169],"traditional":[170],"methods.":[172],"Compared":[173],"AR":[176],"solution,":[177],"NAR":[179],"reduces":[181],"size":[183],"43.2%":[185],"speeds":[187],"up":[188],"inference":[189],"2.1":[191],"times.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}