{"id":"https://openalex.org/W4385477881","doi":"https://doi.org/10.1109/icasspw59220.2023.10193184","title":"Measuring the Impact of Domain Factors in Self-Supervised Pre-Training","display_name":"Measuring the Impact of Domain Factors in Self-Supervised Pre-Training","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385477881","doi":"https://doi.org/10.1109/icasspw59220.2023.10193184"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5053704856","display_name":"Ramon Sanabria","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ramon Sanabria","raw_affiliation_strings":["The University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7040461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8130336403846741},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6691678762435913},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5833092927932739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.573764443397522},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5688993334770203},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5552583932876587},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5356879234313965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.531936526298523},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4881921410560608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48311328887939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130336403846741},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6691678762435913},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5833092927932739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.573764443397522},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5688993334770203},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5552583932876587},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5356879234313965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.531936526298523},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4881921410560608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48311328887939453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2933138175","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3104570641","https://openalex.org/W3140429000","https://openalex.org/W3180374548","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3198771897","https://openalex.org/W3201490875","https://openalex.org/W3209059054","https://openalex.org/W4206711328","https://openalex.org/W4287854499","https://openalex.org/W4375869012","https://openalex.org/W6603931906","https://openalex.org/W6778823374","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6783125911","https://openalex.org/W6783867762","https://openalex.org/W6791823829","https://openalex.org/W6798080464","https://openalex.org/W6810419249"],"related_works":["https://openalex.org/W2046075387","https://openalex.org/W2789919619","https://openalex.org/W4235530921","https://openalex.org/W2293457016","https://openalex.org/W2004207941","https://openalex.org/W3169305685","https://openalex.org/W4385553535","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738"],"abstract_inverted_index":{"Human":[0],"speech":[1,30,73,85],"data":[2],"comprises":[3],"a":[4,37,54,90],"rich":[5],"set":[6],"of":[7,25,46,62,68,136],"domain":[8,26,92,105,134],"factors":[9,64,106,117],"such":[10,63],"as":[11,36],"accent,":[12],"syntactic":[13,116],"and":[14,34,95,115],"semantic":[15],"variety,":[16],"or":[17,86],"acoustic":[18],"environment.":[19],"Previous":[20],"work":[21],"explores":[22],"the":[23,44,60,66,127,133],"effect":[24,61],"mismatch":[27],"in":[28,139],"automatic":[29,72],"recognition":[31],"between":[32],"pre-training":[33,112,141],"fine-tuning":[35],"whole":[38],"[1]":[39],"but":[40],"does":[41],"not":[42],"dissect":[43],"contribution":[45],"individual":[47],"factors.":[48],"In":[49],"this":[50,125],"paper,":[51],"we":[52,78],"present":[53],"controlled":[55],"study":[56,129],"to":[57,130],"better":[58,131],"understand":[59,132],"on":[65,71,82],"performance":[67,98],"pre-trained":[69,137],"representations":[70],"recognition.":[74],"To":[75,122],"do":[76],"so,":[77],"pre-train":[79],"models":[80],"either":[81],"modified":[83],"natural":[84],"synthesized":[87],"audio,":[88],"with":[89],"single":[91],"factor":[93],"modified,":[94],"then":[96],"measure":[97],"after":[99],"fine-tuning.":[100],"Results":[101],"show":[102],"that":[103],"phonetic":[104],"play":[107],"an":[108],"important":[109],"role":[110],"during":[111],"while":[113],"grammatical":[114],"are":[118],"far":[119],"less":[120],"important.":[121],"our":[123],"knowledge,":[124],"is":[126],"first":[128],"characteristics":[135],"sets":[138],"self-supervised":[140],"for":[142],"speech.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}