{"id":"https://openalex.org/W4406462041","doi":"https://doi.org/10.1109/slt61566.2024.10832361","title":"Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget","display_name":"Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462041","doi":"https://doi.org/10.1109/slt61566.2024.10832361"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/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,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083437044","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0000-0002-5130-5280"},"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-Cheng Lin","raw_affiliation_strings":["National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082226990","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0002-2453-3691"},"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":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018017185","display_name":"Stefan Winkler","orcid":"https://orcid.org/0000-0003-4305-8408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Winkler","raw_affiliation_strings":["ASUS Intelligent Cloud Services (AICS),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASUS Intelligent Cloud Services (AICS),Singapore","institution_ids":[]}]},{"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,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"961","last_page":"968"},"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":0.9988999962806702,"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":0.9933000206947327,"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/foundation","display_name":"Foundation (evidence)","score":0.7495137453079224},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060073614120483},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4981346130371094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39504918456077576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3619316816329956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3422009348869324}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7495137453079224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060073614120483},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4981346130371094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39504918456077576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3619316816329956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3422009348869324},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316499","display_name":"National Applied Research Laboratories","ror":"https://ror.org/05wcstg80"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2972943112","https://openalex.org/W2982223350","https://openalex.org/W3016181583","https://openalex.org/W3041561163","https://openalex.org/W3096017728","https://openalex.org/W3097286738","https://openalex.org/W3102342027","https://openalex.org/W3148040514","https://openalex.org/W3162133897","https://openalex.org/W3166440012","https://openalex.org/W3183764363","https://openalex.org/W3197580070","https://openalex.org/W3198858531","https://openalex.org/W3200129129","https://openalex.org/W3203140070","https://openalex.org/W3206559778","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225591000","https://openalex.org/W4281492411","https://openalex.org/W4285250921","https://openalex.org/W4293363567","https://openalex.org/W4297808394","https://openalex.org/W4297841557","https://openalex.org/W4297841794","https://openalex.org/W4319862456","https://openalex.org/W4375869065","https://openalex.org/W4385822254","https://openalex.org/W4385823426","https://openalex.org/W4385823507","https://openalex.org/W4391021746","https://openalex.org/W4394862910","https://openalex.org/W4399694394","https://openalex.org/W4402112198","https://openalex.org/W4402112459","https://openalex.org/W6680300913","https://openalex.org/W6780218876","https://openalex.org/W6810220367","https://openalex.org/W6844194202","https://openalex.org/W6869487681"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Despite":[0],"their":[1],"impressive":[2],"success,":[3],"training":[4,57],"foundation":[5,18,61],"models":[6,19],"remains":[7,112],"computationally":[8],"costly.":[9],"This":[10],"paper":[11],"investigates":[12],"how":[13],"to":[14,50,80],"efficiently":[15],"train":[16],"speech":[17,60],"with":[20,115],"self-supervised":[21],"learning":[22],"(SSL)":[23],"under":[24,96],"a":[25,132,146],"limited":[26,127],"compute":[27,99,148],"budget.":[28,102,149],"We":[29,63,103],"examine":[30],"critical":[31],"factors":[32,76],"in":[33,67],"SSL":[34,65,119],"that":[35,74,88,105],"impact":[36],"the":[37,56,81,97,106,109],"budget,":[38],"including":[39],"model":[40,42,90,135,143],"architecture,":[41],"size,":[43,139],"and":[44,72,100,137],"data":[45,111,116,138],"size.":[46],"Our":[47,85],"goal":[48],"is":[49],"make":[51],"analytical":[52],"steps":[53],"toward":[54],"understanding":[55],"dynamics":[58],"of":[59,83,108],"models.":[62],"benchmark":[64],"objectives":[66],"an":[68,141],"entirely":[69],"comparable":[70],"setting":[71],"find":[73],"other":[75],"contribute":[77],"more":[78],"significantly":[79],"success":[82],"SSL.":[84],"results":[86],"show":[87],"slimmer":[89],"architectures":[91,95],"outperform":[92],"common":[93],"small":[94],"same":[98],"parameter":[101],"demonstrate":[104],"size":[107,136,144],"pre-training":[110],"crucial,":[113],"even":[114],"augmentation":[117],"during":[118],"training,":[120],"as":[121],"performance":[122],"suffers":[123],"when":[124],"iterating":[125],"over":[126],"data.":[128],"Finally,":[129],"we":[130],"identify":[131],"trade-off":[133],"between":[134],"highlighting":[140],"optimal":[142],"for":[145],"given":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}