{"id":"https://openalex.org/W4312849149","doi":"https://doi.org/10.1109/access.2022.3219838","title":"Automatic Speech Recognition Post-Processing for Readability: Task, Dataset and a Two-Stage Pre-Trained Approach","display_name":"Automatic Speech Recognition Post-Processing for Readability: Task, Dataset and a Two-Stage Pre-Trained Approach","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312849149","doi":"https://doi.org/10.1109/access.2022.3219838"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3219838","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3219838","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09940272.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09940272.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078591720","display_name":"Junwei Liao","orcid":"https://orcid.org/0000-0001-7321-7583"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwei Liao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7321-7583","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597408","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1872-3429"},"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":"Yu Shi","raw_affiliation_strings":["Microsoft Cognitive Services Research Group, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Cognitive Services Research Group, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111751049","display_name":"Yong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098616","display_name":"Chengdu Guoke Haibo Information Technology (China)","ror":"https://ror.org/0148z7881","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Westone Information Industry Inc., Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westone Information Industry Inc., Chengdu, China","institution_ids":["https://openalex.org/I4210098616"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2624,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62506285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"10","issue":null,"first_page":"117053","last_page":"117066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T13629","display_name":"Text Readability and Simplification","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.8841443657875061},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.7104741334915161},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6101030111312866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6098795533180237},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.603023111820221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5715758204460144},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5403075814247131},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5077608823776245},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4421968162059784},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4251711964607239},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4169941842556},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4125271439552307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841443657875061},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.7104741334915161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6101030111312866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098795533180237},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.603023111820221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5715758204460144},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5403075814247131},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5077608823776245},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4421968162059784},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4251711964607239},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4169941842556},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4125271439552307},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3219838","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3219838","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09940272.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a36a71c126324d67b8ebfe466add04aa","is_oa":true,"landing_page_url":"https://doaj.org/article/a36a71c126324d67b8ebfe466add04aa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 117053-117066 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3219838","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3219838","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09940272.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312849149.pdf","grobid_xml":"https://content.openalex.org/works/W4312849149.grobid-xml"},"referenced_works_count":113,"referenced_works":["https://openalex.org/W26608090","https://openalex.org/W98892075","https://openalex.org/W145178388","https://openalex.org/W157500369","https://openalex.org/W196317654","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1600744878","https://openalex.org/W1721115786","https://openalex.org/W1828163288","https://openalex.org/W2003123121","https://openalex.org/W2064675550","https://openalex.org/W2101446498","https://openalex.org/W2103085228","https://openalex.org/W2113410090","https://openalex.org/W2119071713","https://openalex.org/W2123343069","https://openalex.org/W2124725212","https://openalex.org/W2125616599","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2142112143","https://openalex.org/W2144950812","https://openalex.org/W2151742940","https://openalex.org/W2157331557","https://openalex.org/W2169187092","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2394620515","https://openalex.org/W2396384435","https://openalex.org/W2402268235","https://openalex.org/W2407834842","https://openalex.org/W2507699225","https://openalex.org/W2608712415","https://openalex.org/W2750499125","https://openalex.org/W2797303992","https://openalex.org/W2810035278","https://openalex.org/W2841603554","https://openalex.org/W2896457183","https://openalex.org/W2903853691","https://openalex.org/W2916979304","https://openalex.org/W2916997151","https://openalex.org/W2931749839","https://openalex.org/W2939976383","https://openalex.org/W2945260553","https://openalex.org/W2952468927","https://openalex.org/W2952729433","https://openalex.org/W2963026768","https://openalex.org/W2963882470","https://openalex.org/W2964243274","https://openalex.org/W2965373594","https://openalex.org/W2970076840","https://openalex.org/W2970597249","https://openalex.org/W2970868759","https://openalex.org/W2972529197","https://openalex.org/W2972799129","https://openalex.org/W2973122799","https://openalex.org/W3015752032","https://openalex.org/W3016155933","https://openalex.org/W3018962734","https://openalex.org/W3034999214","https://openalex.org/W3035451444","https://openalex.org/W3104020052","https://openalex.org/W3160789530","https://openalex.org/W3161127962","https://openalex.org/W3168796983","https://openalex.org/W3171697871","https://openalex.org/W3175441946","https://openalex.org/W3185027180","https://openalex.org/W3202167223","https://openalex.org/W3202802636","https://openalex.org/W4221167110","https://openalex.org/W4224308101","https://openalex.org/W4288089799","https://openalex.org/W4288366473","https://openalex.org/W4292779060","https://openalex.org/W4302343710","https://openalex.org/W4385245566","https://openalex.org/W6601052561","https://openalex.org/W6604003587","https://openalex.org/W6605854414","https://openalex.org/W6607995579","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6678346093","https://openalex.org/W6678481887","https://openalex.org/W6679436768","https://openalex.org/W6681661476","https://openalex.org/W6685158001","https://openalex.org/W6696934422","https://openalex.org/W6711742426","https://openalex.org/W6714054690","https://openalex.org/W6739901393","https://openalex.org/W6742080785","https://openalex.org/W6752756761","https://openalex.org/W6753036352","https://openalex.org/W6755207826","https://openalex.org/W6757322325","https://openalex.org/W6761584544","https://openalex.org/W6762122294","https://openalex.org/W6762521896","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6767485738","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6799367816","https://openalex.org/W6802354036","https://openalex.org/W6803034309","https://openalex.org/W6810081322","https://openalex.org/W6810296985","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W4290708361","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W2129812225","https://openalex.org/W1507733787","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Nowadays":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"can":[6,197],"accurately":[7],"recognize":[8],"which":[9,34],"words":[10],"are":[11],"said.":[12],"However,":[13],"due":[14],"to":[15,46,75,98,143,157],"the":[16,26,48,61,77,93,108,128,139,145,150,160,164,171,203],"disfluency,":[17],"grammatical":[18,129],"error,":[19],"and":[20,40,50,79,88,148,183],"other":[21],"phenomena":[22],"in":[23],"spontaneous":[24],"speech,":[25],"verbatim":[27],"transcription":[28],"of":[29,52,110,179],"ASR":[30,62,81],"impairs":[31],"its":[32],"readability,":[33],"is":[35,54],"crucial":[36],"for":[37,64,86,103],"human":[38,190],"comprehension":[39],"downstream":[41,89],"tasks":[42],"processing":[43],"that":[44,73,122,194],"need":[45],"understand":[47],"meaning":[49],"purpose":[51],"what":[53],"spoken.":[55],"In":[56],"this":[57],"work,":[58],"we":[59,115],"formulate":[60],"post-processing":[63],"readability":[65],"(APR)":[66],"as":[67],"a":[68,100,117,135,153,176],"sequence-to-sequence":[69],"text":[70,85],"generation":[71],"problem":[72,109],"aims":[74],"transform":[76],"incorrect":[78],"noisy":[80],"output":[82],"into":[83],"readable":[84],"humans":[87],"tasks.":[90],"We":[91,133],"leverage":[92],"Metadata":[94],"Extraction":[95],"(MDE)":[96],"corpus":[97],"construct":[99],"task-specific":[101],"dataset":[102],"our":[104,168,195],"study.":[105],"To":[106],"solve":[107],"too":[111],"little":[112],"training":[113,125,155],"data,":[114],"propose":[116,134],"novel":[118],"data":[119,126],"augmentation":[120],"method":[121],"synthesizes":[123],"large-scale":[124],"from":[127],"error":[130],"correction":[131],"dataset.":[132],"model":[136,142,151,196],"based":[137],"on":[138,181,185],"pre-trained":[140],"language":[141],"perform":[144],"APR":[146],"task":[147],"train":[149],"with":[152],"two-stage":[154],"strategy":[156],"better":[158],"exploit":[159],"augmented":[161],"data.":[162],"On":[163],"constructed":[165],"test":[166],"set,":[167],"approach":[169],"outperforms":[170],"best":[172],"baseline":[173,204],"system":[174],"by":[175],"large":[177],"margin":[178],"17.53":[180],"BLEU":[182],"13.26":[184],"readability-aware":[186],"WER":[187],"(RA-WER).":[188],"The":[189],"evaluation":[191],"also":[192],"shows":[193],"generate":[198],"more":[199],"human-readable":[200],"transcripts":[201],"than":[202],"method.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}