{"id":"https://openalex.org/W3152575505","doi":"https://doi.org/10.21437/interspeech.2021-739","title":"BART Based Semantic Correction for Mandarin Automatic Speech Recognition System","display_name":"BART Based Semantic Correction for Mandarin Automatic Speech Recognition System","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3152575505","doi":"https://doi.org/10.21437/interspeech.2021-739","mag":"3152575505"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-739","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.05507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010611229","display_name":"Yun Zhao","orcid":"https://orcid.org/0000-0001-7468-890X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun Zhao","raw_affiliation_strings":["Arizona State University, Tempe, United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045682980","display_name":"Xuerui Yang","orcid":"https://orcid.org/0000-0002-7731-2147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuerui Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076960417","display_name":"Jinchao Wang","orcid":"https://orcid.org/0000-0003-1294-5186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085408243","display_name":"Yongyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongyu Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101539312","display_name":"Chao Yan","orcid":"https://orcid.org/0000-0002-7482-9116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108850","display_name":"Yuanfu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanfu Zhou","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010611229"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04479692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2017","last_page":"2021"},"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.8321808576583862},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7645518779754639},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7339290380477905},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7237138748168945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6764644384384155},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6514546871185303},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5926963090896606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5619835257530212},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5552051663398743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06985205411911011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321808576583862},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7645518779754639},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7339290380477905},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7237138748168945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6764644384384155},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6514546871185303},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5926963090896606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619835257530212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5552051663398743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06985205411911011},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":4,"locations":[{"id":"doi:10.21437/interspeech.2021-739","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.05507","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05507","pdf_url":"https://arxiv.org/pdf/2104.05507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3152575505","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.05507v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.05507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.05507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.05507","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05507","pdf_url":"https://arxiv.org/pdf/2104.05507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1524333225","https://openalex.org/W1633171621","https://openalex.org/W2797303992","https://openalex.org/W2885213066","https://openalex.org/W2898181186","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2972625221","https://openalex.org/W2972650231","https://openalex.org/W2982399380","https://openalex.org/W3003809177","https://openalex.org/W3010917970","https://openalex.org/W3015752032","https://openalex.org/W3024680312","https://openalex.org/W3210120707"],"related_works":["https://openalex.org/W3196313137","https://openalex.org/W3209868296","https://openalex.org/W2358723637","https://openalex.org/W2810782704","https://openalex.org/W3034252112","https://openalex.org/W2762590475","https://openalex.org/W2618015847","https://openalex.org/W2941602825","https://openalex.org/W1491807228","https://openalex.org/W2506773476","https://openalex.org/W3048912752","https://openalex.org/W2898727538","https://openalex.org/W2944150351","https://openalex.org/W3161127962","https://openalex.org/W2303868227","https://openalex.org/W3015752032","https://openalex.org/W2402238668","https://openalex.org/W2963230678","https://openalex.org/W3124354403","https://openalex.org/W2137862343"],"abstract_inverted_index":{"Although":[0],"automatic":[1],"speech":[2,59],"recognition":[3,14,34],"(ASR)":[4],"systems":[5],"achieved":[6],"significantly":[7],"improvements":[8],"in":[9],"recent":[10],"years,":[11],"spoken":[12],"language":[13,26],"error":[15,64],"occurs":[16],"which":[17],"can":[18,67],"be":[19,68],"easily":[20],"spotted":[21],"by":[22,71],"human":[23],"beings.":[24],"Various":[25],"modeling":[27],"techniques":[28],"have":[29],"been":[30],"developed":[31],"on":[32,55],"post":[33],"tasks":[35],"like":[36],"semantic":[37,47],"correction.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"a":[44],"Transformer":[45],"based":[46],"correction":[48],"method":[49],"with":[50],"pretrained":[51],"BART":[52],"initialization,":[53],"Experiments":[54],"10000":[56],"hours":[57],"Mandarin":[58],"dataset":[60],"show":[61],"that":[62,83],"character":[63],"rate":[65],"(CER)":[66],"effectively":[69],"reduced":[70],"21.7%":[72],"relatively":[73],"compared":[74],"to":[75],"our":[76,87],"baseline":[77],"ASR":[78],"system.":[79],"Expert":[80],"evaluation":[81],"demonstrates":[82],"actual":[84],"improvement":[85],"of":[86],"model":[88],"surpasses":[89],"what":[90],"CER":[91],"indicates.":[92]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}