{"id":"https://openalex.org/W3161048756","doi":"https://doi.org/10.1109/icassp39728.2021.9413668","title":"Speech Recognition by Simply Fine-Tuning Bert","display_name":"Speech Recognition by Simply Fine-Tuning Bert","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161048756","doi":"https://doi.org/10.1109/icassp39728.2021.9413668","mag":"3161048756"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP","TW"],"is_corresponding":true,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Academia Sinica, Taiwan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024882790","display_name":"Chia-Hua Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hua Wu","raw_affiliation_strings":["Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067529162","display_name":"Shang-Bao Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shang-Bao Luo","raw_affiliation_strings":["Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603153","display_name":"Kuan\u2010Yu Chen","orcid":"https://orcid.org/0000-0002-6036-2199"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000377034"],"corresponding_institution_ids":["https://openalex.org/I60134161","https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":3.0798,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92715446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7343","last_page":"7347"},"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":0.9994999766349792,"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":0.9991000294685364,"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":0.8439764976501465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7125310897827148},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.6845122575759888},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6570494771003723},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6438602209091187},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5375022888183594},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5163489580154419},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.511809766292572},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4657056927680969},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4383329451084137},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4192703366279602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40938588976860046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33660000562667847},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2992437779903412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439764976501465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7125310897827148},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.6845122575759888},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6570494771003723},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6438602209091187},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5375022888183594},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5163489580154419},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.511809766292572},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4657056927680969},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4383329451084137},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4192703366279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40938588976860046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2992437779903412},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2896457183","https://openalex.org/W2909544278","https://openalex.org/W2924690340","https://openalex.org/W2936123380","https://openalex.org/W2936695845","https://openalex.org/W2946434750","https://openalex.org/W2963242190","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2973840669","https://openalex.org/W2980282514","https://openalex.org/W2990391581","https://openalex.org/W2994928925","https://openalex.org/W2996403597","https://openalex.org/W2996428491","https://openalex.org/W2998385486","https://openalex.org/W3006057906","https://openalex.org/W3006381853","https://openalex.org/W3016167541","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3034961030","https://openalex.org/W3096297644","https://openalex.org/W3102725307","https://openalex.org/W3105451204","https://openalex.org/W4300427681","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6758015726","https://openalex.org/W6761205521","https://openalex.org/W6761268247","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6770528390","https://openalex.org/W6771713106","https://openalex.org/W6773830248","https://openalex.org/W6785794352"],"related_works":["https://openalex.org/W3037551068","https://openalex.org/W3023285645","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W2126322296","https://openalex.org/W2955724459","https://openalex.org/W2163537793","https://openalex.org/W2037769829","https://openalex.org/W3154646238","https://openalex.org/W2916997151"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,15,36,40,58,69,86,109],"simple":[3,59,111],"method":[4],"for":[5],"automatic":[6],"speech":[7,52,79],"recognition":[8,80],"(ASR)":[9],"by":[10,83],"fine-tuning":[11,85],"BERT,":[12],"which":[13],"is":[14,33,81],"language":[16],"model":[17,72],"(LM)":[18],"trained":[19],"on":[20,101,113],"large-scale":[21],"unlabeled":[22],"text":[23],"data":[24],"and":[25,50,105],"can":[26,43,54,117],"generate":[27],"rich":[28],"contextual":[29],"representations.":[30],"Our":[31],"assumption":[32],"that":[34,67,78,107],"given":[35],"history":[37],"context":[38],"sequence,":[39],"powerful":[41,70],"LM":[42],"narrow":[44],"the":[45,51,95,98,102],"range":[46],"of":[47,97,115],"possible":[48,82],"choices":[49],"signal":[53],"be":[55],"used":[56],"as":[57],"clue.":[60],"Hence,":[61],"comparing":[62],"to":[63],"conventional":[64],"ASR":[65],"systems":[66],"train":[68],"acoustic":[71],"(AM)":[73],"from":[74],"scratch,":[75],"we":[76,93],"believe":[77],"simply":[84],"BERT":[87,116],"model.":[88],"As":[89],"an":[90],"initial":[91],"study,":[92],"demonstrate":[94],"effectiveness":[96],"proposed":[99],"idea":[100],"AISHELL":[103],"dataset":[104],"show":[106],"stacking":[108],"very":[110],"AM":[112],"top":[114],"yield":[118],"reasonable":[119],"performance.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}