{"id":"https://openalex.org/W4319862404","doi":"https://doi.org/10.1109/slt54892.2023.10022991","title":"On Compressing Sequences for Self-Supervised Speech Models","display_name":"On Compressing Sequences for Self-Supervised Speech Models","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862404","doi":"https://doi.org/10.1109/slt54892.2023.10022991"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022991","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022991","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067668991","display_name":"Hsuan-Jui Chen","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":"Hsuan-Jui Chen","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"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":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"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":"Hao Tang","raw_affiliation_strings":["The University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062573067"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.0189,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74076002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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":0.8028683066368103},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7266442179679871},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5596134662628174},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5402116775512695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5264443159103394},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.47883012890815735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4466524124145508},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4411333501338959},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.4200015068054199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36811795830726624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3578758239746094},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16937768459320068},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07487419247627258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028683066368103},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7266442179679871},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5596134662628174},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5402116775512695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264443159103394},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.47883012890815735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4466524124145508},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4411333501338959},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4200015068054199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36811795830726624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3578758239746094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16937768459320068},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07487419247627258},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/slt54892.2023.10022991","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022991","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2010291496","https://openalex.org/W2190506272","https://openalex.org/W2296681920","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2627092829","https://openalex.org/W2747874407","https://openalex.org/W2802023636","https://openalex.org/W2916113431","https://openalex.org/W2933138175","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963250244","https://openalex.org/W3015468748","https://openalex.org/W3016167541","https://openalex.org/W3036601975","https://openalex.org/W3085139254","https://openalex.org/W3112034174","https://openalex.org/W3134881075","https://openalex.org/W3197580070","https://openalex.org/W3197974236","https://openalex.org/W3198134274","https://openalex.org/W3198782837","https://openalex.org/W3200129129","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4287173589","https://openalex.org/W4287704453","https://openalex.org/W4297841557","https://openalex.org/W4297841794","https://openalex.org/W4319862670","https://openalex.org/W4394671563","https://openalex.org/W6638523607","https://openalex.org/W6729956949","https://openalex.org/W6751979845","https://openalex.org/W6776048684","https://openalex.org/W6780218876","https://openalex.org/W6781533629","https://openalex.org/W6786669483","https://openalex.org/W6790356757","https://openalex.org/W6791299810","https://openalex.org/W6795952400","https://openalex.org/W6810007534","https://openalex.org/W6849880362"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W2055438207","https://openalex.org/W2521424917","https://openalex.org/W3040203686","https://openalex.org/W4249524554","https://openalex.org/W2349021146","https://openalex.org/W2977517636","https://openalex.org/W1969179582","https://openalex.org/W2810129309"],"abstract_inverted_index":{"Compressing":[0],"self-supervised":[1,8,47,64],"models":[2,9,65],"has":[3],"become":[4,10],"increasingly":[5],"necessary,":[6],"as":[7,115,117],"larger.":[11],"While":[12],"previous":[13],"approaches":[14],"have":[15,99],"primarily":[16],"focused":[17],"on":[18,72],"compressing":[19],"the":[20,30,43,69],"model":[21],"size,":[22],"shortening":[23],"sequences":[24],"is":[25],"also":[26,80],"effective":[27],"in":[28,46,84,108],"reducing":[29],"computational":[31],"cost.":[32],"In":[33,95],"this":[34],"work,":[35],"we":[36,98,104],"study":[37],"fixed-length":[38],"and":[39],"variable-length":[40],"subsampling":[41,87],"along":[42],"time":[44],"axis":[45],"learning.":[48],"We":[49],"explore":[50],"how":[51],"individual":[52],"downstream":[53,73],"tasks":[54,74],"are":[55],"sensitive":[56],"to":[57,101],"input":[58],"frame":[59,77,93,113],"rates.":[60,94],"Subsampling":[61],"while":[62],"training":[63],"not":[66],"only":[67],"improves":[68],"overall":[70],"performance":[71,109],"under":[75,91],"certain":[76],"rates,":[78],"but":[79],"brings":[81],"significant":[82],"speed-up":[83],"inference.":[85],"Variable-length":[86],"performs":[88],"particularly":[89],"well":[90],"low":[92,116],"addition,":[96],"if":[97],"access":[100],"phonetic":[102],"boundaries,":[103],"find":[105],"no":[106],"degradation":[107],"for":[110],"an":[111],"average":[112],"rate":[114],"10":[118],"Hz.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}