{"id":"https://openalex.org/W4293793697","doi":"https://doi.org/10.1109/jstsp.2022.3200910","title":"Towards Better Domain Adaptation for Self-Supervised Models: A Case Study of Child ASR","display_name":"Towards Better Domain Adaptation for Self-Supervised Models: A Case Study of Child ASR","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4293793697","doi":"https://doi.org/10.1109/jstsp.2022.3200910"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3200910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200910","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.00115","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080637906","display_name":"Ruchao Fan","orcid":"https://orcid.org/0000-0001-5021-2747"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruchao Fan","raw_affiliation_strings":["ECE Department, University of California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5021-2747","affiliations":[{"raw_affiliation_string":"ECE Department, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013701770","display_name":"Yunzheng Zhu","orcid":"https://orcid.org/0009-0006-9143-7137"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunzheng Zhu","raw_affiliation_strings":["ECE Department, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979902","display_name":"Jinhan Wang","orcid":"https://orcid.org/0000-0003-1930-2271"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinhan Wang","raw_affiliation_strings":["ECE Department, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112421995","display_name":"Abeer Alwan","orcid":"https://orcid.org/0000-0003-3390-9379"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abeer Alwan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":3.2025,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92595271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"1242","last_page":"1252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.991599977016449,"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":0.9865999817848206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8065921068191528},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6865697503089905},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6777777671813965},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5557034015655518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49436140060424805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4865066409111023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39202654361724854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37787064909935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065921068191528},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6865697503089905},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6777777671813965},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5557034015655518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49436140060424805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4865066409111023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39202654361724854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37787064909935},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3200910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200910","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"},{"id":"pmh:oai:arXiv.org:2305.00115","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.00115","pdf_url":"https://arxiv.org/pdf/2305.00115","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.00115","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.00115","pdf_url":"https://arxiv.org/pdf/2305.00115","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293793697.pdf","grobid_xml":"https://content.openalex.org/works/W4293793697.grobid-xml"},"referenced_works_count":89,"referenced_works":["https://openalex.org/W17704661","https://openalex.org/W1494198834","https://openalex.org/W1533861849","https://openalex.org/W1538131130","https://openalex.org/W1992152912","https://openalex.org/W1994888226","https://openalex.org/W2005708641","https://openalex.org/W2060277733","https://openalex.org/W2107162140","https://openalex.org/W2111460811","https://openalex.org/W2407080277","https://openalex.org/W2471933213","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2963211188","https://openalex.org/W2964303773","https://openalex.org/W2971840980","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973513151","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2988736778","https://openalex.org/W2995181338","https://openalex.org/W3003875258","https://openalex.org/W3015265920","https://openalex.org/W3015356564","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3035202887","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3096713376","https://openalex.org/W3097053302","https://openalex.org/W3097345069","https://openalex.org/W3113594615","https://openalex.org/W3160345865","https://openalex.org/W3160799772","https://openalex.org/W3161005563","https://openalex.org/W3165404421","https://openalex.org/W3169320628","https://openalex.org/W3174997050","https://openalex.org/W3186596101","https://openalex.org/W3186998975","https://openalex.org/W3189296823","https://openalex.org/W3197580070","https://openalex.org/W3198094329","https://openalex.org/W3198261723","https://openalex.org/W3198447122","https://openalex.org/W3198484663","https://openalex.org/W3198771897","https://openalex.org/W3201225328","https://openalex.org/W3202037040","https://openalex.org/W3202079424","https://openalex.org/W3203098807","https://openalex.org/W3203561692","https://openalex.org/W3204696009","https://openalex.org/W3205533980","https://openalex.org/W3205644108","https://openalex.org/W3206559778","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4214784181","https://openalex.org/W4225274946","https://openalex.org/W4226033575","https://openalex.org/W4283073456","https://openalex.org/W4285761032","https://openalex.org/W4287241171","https://openalex.org/W4287374065","https://openalex.org/W4287989344","https://openalex.org/W4290711009","https://openalex.org/W4297808394","https://openalex.org/W4297841489","https://openalex.org/W4302764113","https://openalex.org/W4308349017","https://openalex.org/W4320169525","https://openalex.org/W6631943919","https://openalex.org/W6632100814","https://openalex.org/W6738045163","https://openalex.org/W6759579507","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6787141514","https://openalex.org/W6788335241","https://openalex.org/W6799245484","https://openalex.org/W6802503112","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W1520183331","https://openalex.org/W2734842993","https://openalex.org/W2168175994","https://openalex.org/W2049473509"],"abstract_inverted_index":{"Recently,":[0],"self-supervised":[1],"learning":[2],"(SSL)":[3],"from":[4,49,110,176],"unlabelled":[5,111,172],"speech":[6,15,84,174],"data":[7,48,112,175],"has":[8],"gained":[9],"increased":[10],"attention":[11],"in":[12,82],"the":[13,39,96,122,129,137,152,162,187,196,202,208,219,228],"automatic":[14],"recognition":[16],"(ASR)":[17],"community.":[18],"Typical":[19],"SSL":[20,34,43,168],"methods":[21,204],"include":[22],"autoregressive":[23],"predictive":[24],"coding":[25],"(APC),":[26],"Wav2vec2.0,":[27],"and":[28,55,75,86,92,144,164,206,216,221],"hidden":[29],"unit":[30],"BERT":[31],"(HuBERT).":[32],"However,":[33],"models":[35,44,169,198,229],"are":[36,45,133,156,191,212],"biased":[37],"to":[38,78,106,118,184,195,227],"pretraining":[40,232],"data.":[41],"When":[42],"finetuned":[46],"with":[47,171],"another":[50],"domain,":[51],"domain":[52,72,80],"shifting":[53,81],"occurs":[54],"might":[56],"cause":[57],"limited":[58],"knowledge":[59],"transfer":[60],"for":[61,89,127,142],"downstream":[62],"tasks.":[63],"In":[64,135],"this":[65],"paper,":[66],"we":[67],"propose":[68],"a":[69,90],"novel":[70],"framework,":[71],"responsible":[73],"adaptation":[74],"finetuning":[76],"(DRAFT),":[77],"reduce":[79],"pretrained":[83,197],"models,":[85],"evaluate":[87],"it":[88],"causal":[91,97],"non-causal":[93,123,149],"transformer.":[94],"For":[95,121],"transformer,":[98,124],"an":[99],"extension":[100],"of":[101,182],"APC":[102,131],"(E-APC)":[103],"is":[104,140],"proposed":[105,203],"learn":[107],"richer":[108],"information":[109],"by":[113],"using":[114,128,167,231],"multiple":[115],"temporally-shifted":[116],"sequences":[117],"perform":[119],"prediction.":[120],"various":[125],"solutions":[126],"bidirectional":[130],"(Bi-APC)":[132],"investigated.":[134],"addition,":[136],"DRAFT":[138],"framework":[139],"examined":[141],"Wav2vec2.0":[143],"HuBERT":[145],"methods,":[146],"which":[147],"use":[148],"transformers":[150],"as":[151],"backbone.":[153],"The":[154,178],"experiments":[155],"conducted":[157],"on":[158,186,218],"child":[159,189],"ASR":[160],"(using":[161],"OGI":[163,220],"MyST":[165,222],"databases)":[166],"trained":[170],"adult":[173],"Librispeech.":[177],"relative":[179,209],"WER":[180,210],"improvements":[181,211],"up":[183],"19.7%":[185],"two":[188],"tasks":[190],"observed":[192],"when":[193,225],"compared":[194,226],"without":[199,230],"adaptation.":[200],"With":[201],"(E-APC":[205],"DRAFT),":[207],"even":[213],"larger":[214],"(30%":[215],"19%":[217],"data,":[223],"respectively)":[224],"methods.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2022-08-31T00:00:00"}