{"id":"https://openalex.org/W4224952741","doi":"https://doi.org/10.1109/icassp43922.2022.9747831","title":"Optimize Wav2vec2s Architecture for Small Training Set Through Analyzing its Pre-Trained Models Attention Pattern","display_name":"Optimize Wav2vec2s Architecture for Small Training Set Through Analyzing its Pre-Trained Models Attention Pattern","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224952741","doi":"https://doi.org/10.1109/icassp43922.2022.9747831","pmid":"https://pubmed.ncbi.nlm.nih.gov/37193061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747831","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10185057/pdf/nihms-1885626.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100322202","display_name":"Chen Liu","orcid":"https://orcid.org/0000-0003-2000-8133"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liu Chen","raw_affiliation_strings":["Oregon Health & Science University,Department of Pediatrics,Portland,Oregon,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University,Department of Pediatrics,Portland,Oregon,USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038300369","display_name":"Meysam Asgari","orcid":"https://orcid.org/0000-0002-7651-8215"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meysam Asgari","raw_affiliation_strings":["Oregon Health & Science University,Department of Pediatrics,Portland,Oregon,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University,Department of Pediatrics,Portland,Oregon,USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021979900","display_name":"Hiroko H. Dodge","orcid":"https://orcid.org/0000-0001-7290-8307"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hiroko H Dodge","raw_affiliation_strings":["Oregon Health & Science University,Department of Neurology,Portland,Oregon,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University,Department of Neurology,Portland,Oregon,USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100322202"],"corresponding_institution_ids":["https://openalex.org/I165690674"],"apc_list":null,"apc_paid":null,"fwci":1.0529,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69973838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2022","issue":null,"first_page":"7112","last_page":"7116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9868999719619751,"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":0.9782000184059143,"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":0.7778189182281494},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.691370964050293},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5995858907699585},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5404515862464905},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5274612903594971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5150896906852722},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4027641713619232},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37470245361328125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778189182281494},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.691370964050293},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5995858907699585},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5404515862464905},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5274612903594971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5150896906852722},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027641713619232},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37470245361328125},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747831","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:37193061","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37193061","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10185057","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10185057","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10185057/pdf/nihms-1885626.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10185057","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10185057","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10185057/pdf/nihms-1885626.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G2217795110","display_name":null,"funder_award_id":"AG024978","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7785896805","display_name":null,"funder_award_id":"AG051628","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8368121986","display_name":null,"funder_award_id":"AG056102","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8467864776","display_name":null,"funder_award_id":"P30 AG024978","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4224952741.pdf","grobid_xml":"https://content.openalex.org/works/W4224952741.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2012710017","https://openalex.org/W2127141656","https://openalex.org/W2164089264","https://openalex.org/W2325237720","https://openalex.org/W2866343820","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2964110616","https://openalex.org/W2970120757","https://openalex.org/W2970900903","https://openalex.org/W2996428491","https://openalex.org/W3015468748","https://openalex.org/W3034561418","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3131922516","https://openalex.org/W3159719190","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6701498492","https://openalex.org/W6739901393","https://openalex.org/W6753640285","https://openalex.org/W6755207826","https://openalex.org/W6767563556","https://openalex.org/W6768021236","https://openalex.org/W6772372951","https://openalex.org/W6776048684","https://openalex.org/W6778883912","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Transformer-based":[0],"automatic":[1],"speech":[2,33],"recognition":[3],"(ASR)":[4],"systems":[5],"have":[6,21],"shown":[7],"their":[8],"success":[9],"in":[10,17],"the":[11,26,48,78,83,96,118],"presence":[12],"of":[13,50,55,85],"large":[14],"datasets.":[15],"But,":[16],"medical":[18],"research,":[19],"we":[20,46,88],"to":[22,94],"create":[23],"ASR":[24],"for":[25,75],"non-typical":[27],"population,":[28],"i.e.":[29],"pre-school":[30],"children":[31],"with":[32,35,111],"disorders,":[34],"small":[36,44],"training":[37,41,92],"dataset.":[38],"To":[39,81],"increase":[40],"efficiency":[42],"on":[43,128,132],"datasets,":[45],"optimize":[47],"architecture":[49,116,120],"Wav2Vec":[51],"2.0,":[52],"a":[53],"variation":[54],"Transformer,":[56],"through":[57],"analyzing":[58],"its":[59],"pre-trained":[60],"model\u2019s":[61],"block-level":[62,68],"attention":[63,105],"pattern.":[64],"We":[65,100],"show":[66],"that":[67],"patterns":[69],"can":[70],"serve":[71],"as":[72,91],"an":[73],"indicator":[74],"narrowing":[76],"down":[77],"optimization":[79],"direction.":[80],"ensure":[82],"reproducibility":[84],"our":[86],"experiments,":[87],"leverage":[89,101],"Librispeech-100-clean":[90],"data":[93,98],"simulate":[95],"limited":[97],"condition.":[99],"two":[102],"techniques,":[103],"local":[104],"mechanism":[106],"and":[107,130],"cross-block":[108],"parameter":[109],"sharing,":[110],"counter-intuitive":[112],"configurations.":[113],"Our":[114],"optimized":[115],"outperforms":[117],"vanilla":[119],"about":[121],"1.8%":[122],"absolute":[123],"word":[124],"error":[125],"rate":[126],"(WER)":[127],"dev-clean":[129],"1.4%":[131],"test-clean.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}