{"id":"https://openalex.org/W4210546692","doi":"https://doi.org/10.1109/asru51503.2021.9688210","title":"Improving ASR Error Correction Using N-Best Hypotheses","display_name":"Improving ASR Error Correction Using N-Best Hypotheses","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210546692","doi":"https://doi.org/10.1109/asru51503.2021.9688210"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688210","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5072001326","display_name":"Linchen Zhu","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":"Linchen Zhu","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106468560","display_name":"Wenjie Liu","orcid":"https://orcid.org/0000-0001-6196-6843"},"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":"Wenjie Liu","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030700843","display_name":"Linquan Liu","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":false,"raw_author_name":"Linquan Liu","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002012113","display_name":"Edward Lin","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":false,"raw_author_name":"Edward Lin","raw_affiliation_strings":["Microsoft China"],"affiliations":[{"raw_affiliation_string":"Microsoft China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072001326"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.0053,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80388858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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":0.7536154389381409},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7241090536117554},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6470513343811035},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5694196820259094},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5447980761528015},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5341668725013733},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5169307589530945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48073887825012207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46390411257743835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4161831736564636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3000022768974304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27398228645324707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12320160865783691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536154389381409},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7241090536117554},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6470513343811035},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5694196820259094},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5447980761528015},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5341668725013733},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5169307589530945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48073887825012207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46390411257743835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4161831736564636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3000022768974304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27398228645324707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12320160865783691},{"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:10.1109/asru51503.2021.9688210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688210","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W10801008","https://openalex.org/W2128967750","https://openalex.org/W2132991150","https://openalex.org/W2507739667","https://openalex.org/W2613904329","https://openalex.org/W2785918467","https://openalex.org/W2810035278","https://openalex.org/W2860591049","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2945260553","https://openalex.org/W2952468927","https://openalex.org/W2963242190","https://openalex.org/W2963250244","https://openalex.org/W2963881719","https://openalex.org/W2964084166","https://openalex.org/W2965373594","https://openalex.org/W2972650231","https://openalex.org/W3001434439","https://openalex.org/W3015722595","https://openalex.org/W3015752032","https://openalex.org/W3016256870","https://openalex.org/W3035023562","https://openalex.org/W3093312917","https://openalex.org/W3105804405","https://openalex.org/W4385245566","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6753036352","https://openalex.org/W6755207826","https://openalex.org/W6762122294","https://openalex.org/W6762521896","https://openalex.org/W6766673545","https://openalex.org/W6775945549"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2347897961","https://openalex.org/W2979236518","https://openalex.org/W2980068837","https://openalex.org/W2098872742","https://openalex.org/W168676510"],"abstract_inverted_index":{"In":[0,80,101],"the":[1,29,48,52,56,132,137,158,179],"field":[2],"of":[3,21,139],"Automatic":[4],"Speech":[5],"Recognition":[6],"(ASR),":[7],"Grammatical":[8],"Error":[9],"Correction":[10],"(GEC)":[11],"can":[12,107,122],"be":[13,123],"used":[14],"to":[15,69],"correct":[16],"errors":[17,71],"in":[18,55,72],"recognition":[19,45],"results":[20],"ASR":[22,49],"systems":[23],"and":[24,97,117,131,146,170],"whereby":[25],"it":[26],"further":[27],"reduces":[28],"word":[30],"error":[31],"rate":[32],"(WER).":[33],"Most":[34],"conventional":[35,112],"GEC":[36,67,87,182],"approaches":[37,88,106,113,149],"make":[38],"correction":[39],"merely":[40],"based":[41],"on":[42,126,161,166,173],"a":[43,73,185],"single":[44],"hypothesis":[46],"from":[47],"system,":[50],"i.e.,":[51],"best":[53,159],"path":[54],"decoding":[57],"lattice.":[58],"However,":[59],"with":[60,114],"such":[61],"limited":[62],"information,":[63],"it's":[64],"common":[65],"that":[66],"fails":[68],"detect":[70],"sentence":[74],"or":[75],"even":[76],"makes":[77],"wrong":[78],"corrections.":[79],"this":[81,102],"paper":[82],"we":[83],"propose":[84],"two":[85],"novel":[86,105],"utilizing":[89],"N-best":[90,94,98,140,144,147,154],"hypotheses":[91],"instead,":[92],"that's,":[93],"plain":[95,145],"approach":[96,156,183],"alignment":[99,148,155],"approach.":[100],"way,":[103],"our":[104],"access":[108],"more":[109,119],"information":[110],"than":[111],"1-best-only":[115],"hypothesis,":[116],"thus":[118],"accurate":[120],"corrections":[121],"made.":[124],"Experiments":[125],"an":[127,167],"industrial-scale":[128],"internal":[129,168],"dataset":[130,134,169],"open-source":[133],"AISHELL-1":[135],"demonstrate":[136],"effectiveness":[138],"approaches:":[141],"1)":[142],"both":[143,162],"achieve":[150],"remarkable":[151],"WER":[152],"reduction.":[153],"achieves":[157],"performance":[160],"datasets,":[163],"12.54%":[164],"WERR":[165,172],"27.71%":[171],"AISHELL-1.":[174],"2)":[175],"They":[176],"also":[177],"outperform":[178],"baseline":[180],"1-best":[181],"by":[184],"large":[186],"margin.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}