{"id":"https://openalex.org/W3199531394","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533587","title":"Transfer Ability of Monolingual Wav2vec2.0 for Low-resource Speech Recognition","display_name":"Transfer Ability of Monolingual Wav2vec2.0 for Low-resource Speech Recognition","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199531394","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533587","mag":"3199531394"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5101927047","display_name":"Yi Cheng","orcid":"https://orcid.org/0000-0002-5851-1167"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Yi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology Co., Ltd.,Shenzhen,China","Ping An Technology Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology Co., Ltd.,Shenzhen,China","Ping An Technology Co., Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101400153","display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Zhou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101927047"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.9588,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88751835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","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":0.8561166524887085},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6533126831054688},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6448851823806763},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.644632875919342},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.597715437412262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5794728994369507},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.56059730052948},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5169407725334167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5135600566864014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112209320068359},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4785374104976654},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4778977632522583},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43888288736343384},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4334973096847534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561166524887085},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6533126831054688},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6448851823806763},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.644632875919342},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.597715437412262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5794728994369507},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.56059730052948},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5169407725334167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5135600566864014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112209320068359},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4785374104976654},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4778977632522583},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43888288736343384},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4334973096847534},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W273093436","https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W1828163288","https://openalex.org/W1846073453","https://openalex.org/W2025198378","https://openalex.org/W2107298017","https://openalex.org/W2133564696","https://openalex.org/W2141820854","https://openalex.org/W2533523411","https://openalex.org/W2746192915","https://openalex.org/W2750545698","https://openalex.org/W2805394970","https://openalex.org/W2808640845","https://openalex.org/W2842511635","https://openalex.org/W2888779557","https://openalex.org/W2891616026","https://openalex.org/W2894835365","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2907380995","https://openalex.org/W2914120296","https://openalex.org/W2921194440","https://openalex.org/W2936078256","https://openalex.org/W2951974815","https://openalex.org/W2953190524","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963897095","https://openalex.org/W2964308564","https://openalex.org/W2971840980","https://openalex.org/W2972943112","https://openalex.org/W2973034126","https://openalex.org/W2973049979","https://openalex.org/W2973180718","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W2995549860","https://openalex.org/W2996383576","https://openalex.org/W3015265920","https://openalex.org/W3016167541","https://openalex.org/W3016181583","https://openalex.org/W3024182269","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3095311338","https://openalex.org/W3099782249","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W3198429080","https://openalex.org/W4297808394","https://openalex.org/W4300191749","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6638749077","https://openalex.org/W6676215431","https://openalex.org/W6679434410","https://openalex.org/W6728841359","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6752194381","https://openalex.org/W6752630080","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6757304564","https://openalex.org/W6759455113","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6769593479","https://openalex.org/W6771812881","https://openalex.org/W6772253010","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W1979583797","https://openalex.org/W3082848404","https://openalex.org/W2372254676","https://openalex.org/W2793679056","https://openalex.org/W2080135837","https://openalex.org/W4283332091","https://openalex.org/W3145050838","https://openalex.org/W2393154870","https://openalex.org/W2044716874","https://openalex.org/W4295705264"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"are":[2,18,27],"several":[3],"domains":[4],"that":[5,149],"have":[6],"their":[7],"own":[8],"feature":[9,59],"extractors,":[10],"such":[11,154,167],"as":[12,155,168],"ResNet,":[13],"BERT,":[14],"and":[15,49,79],"GPT-x,":[16],"which":[17],"widely":[19],"used":[20,138],"for":[21,51],"various":[22],"down-stream":[23],"tasks.":[24,56],"These":[25],"models":[26],"pre-trained":[28,62,93],"on":[29,63,129],"large":[30],"amounts":[31],"of":[32,106],"unlabeled":[33],"data":[34],"by":[35],"self-supervision.":[36],"In":[37,82],"the":[38,64,89,92,118],"speech":[39,54,58],"domain,":[40],"wav2vec2.0":[41,95,140],"starts":[42],"to":[43,87,96],"show":[44],"its":[45],"powerful":[46],"representation":[47],"ability":[48],"feasibility":[50],"ultra-low":[52],"resource":[53],"recognition":[55],"This":[57],"extractor":[60],"is":[61],"monolingual":[65,94],"audiobook":[66],"corpus,":[67],"whereas":[68],"it":[69],"has":[70,141],"not":[71],"been":[72],"thoroughly":[73],"examined":[74],"in":[75,116,139],"real":[76],"spoken":[77,98],"scenarios":[78],"other":[80],"languages.":[81],"this":[83],"work,":[84],"we":[85],"endeavor":[86],"transfer":[88,144],"knowledge":[90],"from":[91],"cross-lingual":[97],"ASR":[99],"tasks":[100],"with":[101,122,133],"less":[102],"than":[103,112,163],"20":[104],"hours":[105],"labeled":[107],"data.":[108],"We":[109,146],"achieve":[110],"more":[111],"20%":[113],"relative":[114],"improvements":[115],"all":[117],"six":[119],"languages":[120],"compared":[121],"previous":[123],"methods,":[124],"establishing":[125],"a":[126,142],"strong":[127],"benchmark":[128],"CALLHOME":[130],"datasets.":[131],"Compared":[132],"supervised":[134],"pre-training,":[135],"self-supervision":[136],"training":[137],"better":[143,161],"ability.":[145],"also":[147],"find":[148],"using":[150],"coarse-grained":[151],"modeling":[152,165],"units,":[153,166],"subword":[156],"or":[157,170],"character,":[158],"usually":[159],"achieves":[160],"results":[162],"fine-grained":[164],"phone":[169],"letter.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}