{"id":"https://openalex.org/W4372260611","doi":"https://doi.org/10.1109/icassp49357.2023.10094687","title":"Context-Aware Fine-Tuning of Self-Supervised Speech Models","display_name":"Context-Aware Fine-Tuning of Self-Supervised Speech Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260611","doi":"https://doi.org/10.1109/icassp49357.2023.10094687"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["ASAPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074393700","display_name":"Felix Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":["ASAPP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9983999729156494,"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":0.8283382654190063},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5829228162765503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5823978185653687},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5148577094078064},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5080935955047607},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5071611404418945},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4976799786090851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49532952904701233},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.41421836614608765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37877434492111206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3495572507381439}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283382654190063},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5829228162765503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5823978185653687},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5148577094078064},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5080935955047607},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5071611404418945},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4976799786090851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49532952904701233},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.41421836614608765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37877434492111206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3495572507381439},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2726515241","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2946764509","https://openalex.org/W2972430654","https://openalex.org/W2972584841","https://openalex.org/W2972943112","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W2996428491","https://openalex.org/W3005910077","https://openalex.org/W3007433671","https://openalex.org/W3036601975","https://openalex.org/W3100460087","https://openalex.org/W3119308075","https://openalex.org/W3197314576","https://openalex.org/W3197580070","https://openalex.org/W3197898596","https://openalex.org/W3198492054","https://openalex.org/W3209059054","https://openalex.org/W4221144554","https://openalex.org/W4226103796","https://openalex.org/W4226315417","https://openalex.org/W4281492411","https://openalex.org/W4283835659","https://openalex.org/W4285704072","https://openalex.org/W4287887773","https://openalex.org/W4296070361","https://openalex.org/W4297808394","https://openalex.org/W6629028937","https://openalex.org/W6755207826","https://openalex.org/W6768021236","https://openalex.org/W6780218876","https://openalex.org/W6802742088"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2055243143","https://openalex.org/W2849310602","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Self-supervised":[0],"pre-trained":[1,73],"transformers":[2],"have":[3],"improved":[4],"the":[5,8,18,30,43,68,77,94,98,123,150,154],"state":[6],"of":[7,13,24,32,45,67,71,118],"art":[9],"on":[10,65],"a":[11,54,62,72,81,140,184,191],"variety":[12],"speech":[14,164,199],"tasks.":[15],"Due":[16],"to":[17,75,112,115,125,130,144],"quadratic":[19],"time":[20,136],"and":[21,52,137,156,171],"space":[22],"complexity":[23],"self-attention,":[25],"they":[26],"usually":[27],"operate":[28],"at":[29,134],"level":[31],"relatively":[33],"short":[34],"(e.g.,":[35],"utterance)":[36],"segments.":[37,120],"In":[38],"this":[39,108],"paper,":[40],"we":[41,101],"study":[42],"use":[44],"context,":[46],"i.e.,":[47],"surrounding":[48,119,132],"segments,":[49],"during":[50,201],"fine-tuning":[51,99,180,186],"propose":[53],"new":[55],"approach":[56,152],"called":[57],"context-aware":[58,179],"fine-tuning.":[59],"We":[60,148],"attach":[61],"context":[63,82,109,116,193],"module":[64],"top":[66],"last":[69],"layer":[70],"model":[74,124],"encode":[76],"whole":[78],"segment":[79],"into":[80],"embedding":[83,110],"vector":[84,111],"which":[85],"is":[86],"then":[87],"used":[88],"as":[89],"an":[90,103],"additional":[91],"feature":[92],"for":[93,159],"final":[95],"prediction.":[96],"During":[97],"stage,":[100],"introduce":[102],"auxiliary":[104],"loss":[105],"that":[106,178,196],"encourages":[107],"be":[113],"similar":[114],"vectors":[117],"This":[121],"allows":[122],"make":[126],"predictions":[127],"without":[128],"access":[129],"these":[131],"segments":[133,200],"inference":[135],"requires":[138],"only":[139,182],"tiny":[141],"overhead":[142],"compared":[143],"standard":[145,185],"fine-tuned":[146],"models.":[147],"evaluate":[149],"proposed":[151],"using":[153],"SLUE":[155],"Librilight":[157],"benchmarks":[158],"several":[160],"downstream":[161],"tasks:":[162],"Automatic":[163],"recognition":[165,169],"(ASR),":[166],"named":[167],"entity":[168],"(NER),":[170],"sentiment":[172],"analysis":[173],"(SA).":[174],"The":[175],"results":[176],"show":[177],"not":[181],"outperforms":[183],"baseline":[187,195],"but":[188],"also":[189],"rivals":[190],"strong":[192],"injection":[194],"uses":[197],"neighboring":[198],"inference.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}