{"id":"https://openalex.org/W3206559778","doi":"https://doi.org/10.1109/icassp43922.2022.9747897","title":"Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models","display_name":"Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206559778","doi":"https://doi.org/10.1109/icassp43922.2022.9747897","mag":"3206559778"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747897","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"],"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/A5062573067","display_name":"Yen Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yen Meng","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering","College of Electrical Engineering and Computer Science, National Taiwan University","Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019548123","display_name":"Yi-Hui Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hui Chou","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018050919","display_name":"Andy T. Liu","orcid":"https://orcid.org/0000-0002-2502-3992"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Andy T. Liu","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering","College of Electrical Engineering and Computer Science, National Taiwan University","Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering","College of Electrical Engineering and Computer Science, National Taiwan University","Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062573067"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.1482,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79275985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3258","last_page":"3262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6390720009803772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5315746068954468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4012370705604553},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3562001585960388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6390720009803772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5315746068954468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4012370705604553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562001585960388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747897","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2146334809","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2928075308","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963759780","https://openalex.org/W2972584841","https://openalex.org/W2981087920","https://openalex.org/W2982223350","https://openalex.org/W3015265920","https://openalex.org/W3016011332","https://openalex.org/W3026842484","https://openalex.org/W3031202003","https://openalex.org/W3035070478","https://openalex.org/W3035202887","https://openalex.org/W3035357389","https://openalex.org/W3041561163","https://openalex.org/W3049256661","https://openalex.org/W3096017728","https://openalex.org/W3096626135","https://openalex.org/W3097286738","https://openalex.org/W3097568057","https://openalex.org/W3112204873","https://openalex.org/W3114056688","https://openalex.org/W3115108114","https://openalex.org/W3135008008","https://openalex.org/W3144173820","https://openalex.org/W3159783145","https://openalex.org/W3160345865","https://openalex.org/W3160799772","https://openalex.org/W3162133897","https://openalex.org/W3164428426","https://openalex.org/W3174086521","https://openalex.org/W3177397495","https://openalex.org/W3197340960","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W4294103325","https://openalex.org/W6750665317","https://openalex.org/W6752726010","https://openalex.org/W6755207826","https://openalex.org/W6778265221","https://openalex.org/W6778691839","https://openalex.org/W6780361010","https://openalex.org/W6782066904","https://openalex.org/W6785000729","https://openalex.org/W6787898146"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Self-supervised":[0],"Speech":[1],"Models":[2],"(S3Ms)":[3],"have":[4,70],"been":[5],"proven":[6],"successful":[7],"in":[8,62],"many":[9],"speech":[10,82,103],"downstream":[11,21,60,92],"tasks,":[12,93],"like":[13],"ASR.":[14],"However,":[15],"how":[16,32],"pretraining":[17],"data":[18,34],"affects":[19,35],"S3Ms\u2019":[20],"behavior":[22],"remains":[23],"an":[24],"unexplored":[25],"issue.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,76],"study":[31],"pre-training":[33,38],"S3Ms":[36,57,69,90,95],"by":[37],"models":[39],"on":[40,58,86],"biased":[41],"datasets":[42],"targeting":[43],"different":[44],"factors":[45],"of":[46,81,89],"speech,":[47],"including":[48],"gender,":[49],"content,":[50],"and":[51,53],"prosody,":[52],"evaluate":[54],"these":[55],"pre-trained":[56],"selected":[59],"tasks":[61],"SUPERB":[63],"Benchmark.":[64],"Our":[65],"experiments":[66],"show":[67,97],"that":[68,78],"tolerance":[71],"toward":[72,100],"gender":[73],"bias.":[74],"Moreover,":[75],"find":[77],"the":[79,87],"content":[80],"has":[83],"little":[84],"impact":[85],"performance":[88],"across":[91],"but":[94],"do":[96],"a":[98,101],"preference":[99],"slower":[102],"rate.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}