{"id":"https://openalex.org/W4361199948","doi":"https://doi.org/10.23919/icact56868.2023.10079686","title":"Chinese ASR and NER Improvement Based on Whisper Fine-Tuning","display_name":"Chinese ASR and NER Improvement Based on Whisper Fine-Tuning","publication_year":2023,"publication_date":"2023-02-19","ids":{"openalex":"https://openalex.org/W4361199948","doi":"https://doi.org/10.23919/icact56868.2023.10079686"},"language":"en","primary_location":{"id":"doi:10.23919/icact56868.2023.10079686","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact56868.2023.10079686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 25th International Conference on Advanced Communication Technology (ICACT)","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/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Technologies CO., LTD,2012 Labs,Beijing,China","2012 Labs, Huawei Technologies CO., LTD, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO., LTD,2012 Labs,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Labs, Huawei Technologies CO., LTD, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671757","display_name":"M. Zhang","orcid":"https://orcid.org/0000-0001-8659-5727"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei Technologies CO., LTD,2012 Labs,Beijing,China","2012 Labs, Huawei Technologies CO., LTD, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO., LTD,2012 Labs,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Labs, Huawei Technologies CO., LTD, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei Technologies CO., LTD,2012 Labs,Beijing,China","2012 Labs, Huawei Technologies CO., LTD, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO., LTD,2012 Labs,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Labs, Huawei Technologies CO., LTD, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090615289","display_name":"Miaomiao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaomiao Ma","raw_affiliation_strings":["Huawei Technologies CO., LTD,2012 Labs,Beijing,China","2012 Labs, Huawei Technologies CO., LTD, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO., LTD,2012 Labs,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Labs, Huawei Technologies CO., LTD, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054537903","display_name":"Ying Qin","orcid":"https://orcid.org/0000-0001-9131-5830"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Qin","raw_affiliation_strings":["Huawei Technologies CO., LTD,2012 Labs,Beijing,China","2012 Labs, Huawei Technologies CO., LTD, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies CO., LTD,2012 Labs,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"2012 Labs, Huawei Technologies CO., LTD, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038736812"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":3.6497,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94258037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9936000108718872,"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":0.8760584592819214},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.653679609298706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6237168908119202},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5664750337600708},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5473248958587646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5154353380203247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46928107738494873},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45910027623176575},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44543176889419556},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.44140326976776123},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4102891683578491},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06279072165489197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8760584592819214},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.653679609298706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6237168908119202},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5664750337600708},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5473248958587646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5154353380203247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46928107738494873},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45910027623176575},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44543176889419556},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.44140326976776123},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4102891683578491},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06279072165489197},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icact56868.2023.10079686","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icact56868.2023.10079686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 25th International Conference on Advanced Communication Technology (ICACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2608377846","https://openalex.org/W2627092829","https://openalex.org/W2914417638","https://openalex.org/W2943357157","https://openalex.org/W2946558277","https://openalex.org/W2962904552","https://openalex.org/W3034379414","https://openalex.org/W3036601975","https://openalex.org/W3095918555","https://openalex.org/W3097777922","https://openalex.org/W3204917342","https://openalex.org/W3210530853","https://openalex.org/W4221139374","https://openalex.org/W4226251829","https://openalex.org/W4246768052","https://openalex.org/W4285107548","https://openalex.org/W4285163683","https://openalex.org/W4285819432","https://openalex.org/W4311000453","https://openalex.org/W4385245566","https://openalex.org/W6752788575","https://openalex.org/W6780218876","https://openalex.org/W6811100430","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572","https://openalex.org/W3098873988"],"abstract_inverted_index":{"Based":[0],"on":[1,37,52,69,111,122],"680k":[2],"hours":[3],"of":[4,129],"weakly":[5],"supervised":[6],"multilingual":[7],"and":[8,26,65,87,114,118,131],"multi-task":[9,119],"speech":[10],"transcription/translation":[11],"data,":[12,117],"Whisper":[13,30,123],"[1]":[14],"has":[15],"developed":[16],"a":[17,32],"robust":[18],"system":[19],"for":[20,78,106],"both":[21],"Automated":[22],"Speech":[23,27],"Recognition":[24],"(ASR)":[25],"Translation":[28],"(ST).":[29],"provides":[31],"simple":[33],"model":[34],"architecture":[35],"based":[36,68,110,121],"Mel":[38],"spectrum":[39],"+":[40,43],"two-layer":[41],"convolution":[42],"Seq2seq":[44],"Transformer":[45],"architecture,":[46],"which":[47],"is":[48],"easy":[49],"to":[50,60,74,84],"fine-tune":[51,61],"conditional":[53],"generation":[54],"tasks.":[55],"This":[56],"paper":[57],"analyzes":[58],"how":[59,73,83],"Chinese":[62],"ASR":[63,86,130],"[2]":[64],"NER":[66,88],"tasks":[67,89],"Whisper,":[70],"including":[71],"(1)":[72],"design":[75],"different":[76,79],"prompts":[77],"generative":[80],"tasks;":[81],"(2)":[82],"train":[85],"at":[90],"the":[91,96,127],"same":[92],"time;":[93],"(3)":[94],"whether":[95],"performance":[97,128],"can":[98,124],"be":[99],"further":[100],"improved":[101],"by":[102],"using":[103],"weak":[104],"supervision":[105],"data":[107],"enhancement.":[108],"Experiments":[109],"AISHELL":[112],"[3]":[113],"AISHELL-NER":[115],"[4]":[116],"fine-tuning":[120],"effectively":[125],"improve":[126],"NER.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}