{"id":"https://openalex.org/W4285144981","doi":"https://doi.org/10.1109/jstsp.2022.3184480","title":"Improving Automatic Speech Recognition Performance for Low-Resource Languages With Self-Supervised Models","display_name":"Improving Automatic Speech Recognition Performance for Low-Resource Languages With Self-Supervised Models","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4285144981","doi":"https://doi.org/10.1109/jstsp.2022.3184480"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3184480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3184480","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5016127800","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0002-3172-2837"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3172-2837","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3841-1959","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":8.8389,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98123319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"16","issue":"6","first_page":"1227","last_page":"1241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9918000102043152,"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":0.9805999994277954,"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":0.8401129245758057},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5561641454696655},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5251333713531494},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5075687170028687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4757765829563141},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4028981328010559},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37389057874679565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8401129245758057},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5561641454696655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5251333713531494},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5075687170028687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4757765829563141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4028981328010559},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37389057874679565},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3184480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3184480","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W1482449999","https://openalex.org/W1494198834","https://openalex.org/W1526974435","https://openalex.org/W1631260214","https://openalex.org/W1991047709","https://openalex.org/W1993660824","https://openalex.org/W2025401819","https://openalex.org/W2079623482","https://openalex.org/W2089917322","https://openalex.org/W2109289099","https://openalex.org/W2127141656","https://openalex.org/W2137630452","https://openalex.org/W2163922914","https://openalex.org/W2184343439","https://openalex.org/W2219249508","https://openalex.org/W2296029621","https://openalex.org/W2406324447","https://openalex.org/W2407080277","https://openalex.org/W2585945212","https://openalex.org/W2766219058","https://openalex.org/W2888825228","https://openalex.org/W2888867175","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963292011","https://openalex.org/W2963979492","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2982223350","https://openalex.org/W2983434507","https://openalex.org/W2995181338","https://openalex.org/W3015213852","https://openalex.org/W3015585292","https://openalex.org/W3016057683","https://openalex.org/W3016181583","https://openalex.org/W3018441253","https://openalex.org/W3041561163","https://openalex.org/W3081416955","https://openalex.org/W3095410713","https://openalex.org/W3097286738","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3122931219","https://openalex.org/W3153263923","https://openalex.org/W3155427814","https://openalex.org/W3163571828","https://openalex.org/W3175898847","https://openalex.org/W3189296823","https://openalex.org/W3196514189","https://openalex.org/W3197278374","https://openalex.org/W3197580070","https://openalex.org/W3198214208","https://openalex.org/W3198429080","https://openalex.org/W3198694222","https://openalex.org/W3198771897","https://openalex.org/W3198800856","https://openalex.org/W3198858531","https://openalex.org/W3205032693","https://openalex.org/W3205710300","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W3213029956","https://openalex.org/W4205767294","https://openalex.org/W4210366248","https://openalex.org/W4226380987","https://openalex.org/W4234453845","https://openalex.org/W4244784864","https://openalex.org/W4287075881","https://openalex.org/W4322714819","https://openalex.org/W6631362777","https://openalex.org/W6635896687","https://openalex.org/W6688816777","https://openalex.org/W6696449567","https://openalex.org/W6733117838","https://openalex.org/W6761472960","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6798423582","https://openalex.org/W6802842272","https://openalex.org/W6803378298","https://openalex.org/W7037943041"],"related_works":["https://openalex.org/W2997512100","https://openalex.org/W2331043530","https://openalex.org/W2961085424","https://openalex.org/W2393933887","https://openalex.org/W4306674287","https://openalex.org/W2374725260","https://openalex.org/W1607315280","https://openalex.org/W4386140649","https://openalex.org/W4224009465","https://openalex.org/W2383403914"],"abstract_inverted_index":{"Speech":[0],"self-supervised":[1],"learning":[2],"has":[3,17,120],"attracted":[4],"much":[5],"attention":[6],"due":[7],"to":[8,145,150],"its":[9],"promising":[10],"performance":[11,93],"in":[12,26,45,49,68,94,112],"multiple":[13],"downstream":[14],"tasks,":[15],"and":[16,34,70,81,85,104,138,147],"become":[18],"a":[19,36,108],"new":[20],"growth":[21],"engine":[22],"for":[23,42,89],"speech":[24,43,91],"recognition":[25,44,92,110],"low-resource":[27,47,95],"languages.":[28,96,140],"In":[29],"this":[30],"paper,":[31],"we":[32,98,115],"exploit":[33],"analyze":[35],"series":[37],"of":[38,107,124],"wav2vec":[39],"pre-trained":[40,74,136,143],"models":[41,75],"15":[46],"languages":[48],"the":[50,105,122],"OpenASR21":[51],"Challenge.":[52],"The":[53,131],"investigation":[54],"covers":[55],"two":[56],"important":[57],"variables":[58],"during":[59],"pre-training,":[60],"three":[61],"fine-tuning":[62,119,139],"methods,":[63],"as":[64,66,160],"well":[65],"applications":[67],"End-to-End":[69,146],"hybrid":[71,148],"systems.":[72],"First,":[73],"with":[76],"different":[77,128,135],"pre-training":[78],"audio":[79],"data":[80,100],"architectures":[82,137],"(wav2vec2.0,":[83],"HuBERT":[84],"WavLM)":[86],"are":[87],"explored":[88],"their":[90],"Second,":[97],"investigate":[99],"utilization,":[101],"multilingual":[102],"learning,":[103],"use":[106],"phoneme-level":[109],"task":[111],"fine-tuning.":[113],"Furthermore,":[114],"explore":[116],"what":[117],"effect":[118],"on":[121],"similarity":[123,132],"representations":[125,144],"extracted":[126],"from":[127],"transformer":[129],"layers.":[130],"analyses":[133],"cover":[134],"We":[141],"apply":[142],"systems":[149],"confirm":[151],"our":[152],"representation":[153],"analyses,":[154],"which":[155],"have":[156],"obtained":[157],"better":[158],"performances":[159],"well.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}