{"id":"https://openalex.org/W4309582373","doi":"https://doi.org/10.1109/asru65441.2025.11434686","title":"Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers","display_name":"Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4309582373","doi":"https://doi.org/10.1109/asru65441.2025.11434686"},"language":"en","primary_location":{"id":"doi:10.1109/asru65441.2025.11434686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.09949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015439080","display_name":"Tzu-Quan Lin","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":"Tzu-Quan Lin","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067252298","display_name":"Tsung-Huan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Huan Yang","raw_affiliation_strings":["Academia Sinica,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064350985","display_name":"Chun-Yao Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Yao Chang","raw_affiliation_strings":["University of California,Los Angeles,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles,United States","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072487344","display_name":"Kuang-Ming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuang-Ming Chen","raw_affiliation_strings":["University of Washington,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,United States","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036438005","display_name":"Tzu-hsun Feng","orcid":"https://orcid.org/0009-0005-1993-6161"},"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":"Tzu-Hsun Feng","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"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":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan","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":["University of Edinburgh,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00033513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.993399977684021,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8247756958007812},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.704004168510437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48144978284835815},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48001307249069214},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.476992666721344},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.46976399421691895},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.4465373754501343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43722081184387207},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.25083789229393005},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.1234026849269867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8247756958007812},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.704004168510437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48144978284835815},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48001307249069214},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.476992666721344},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46976399421691895},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.4465373754501343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43722081184387207},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.25083789229393005},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.1234026849269867},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru65441.2025.11434686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2211.09949","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2211.09949","pdf_url":"https://arxiv.org/pdf/2211.09949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.09949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.09949","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.09949","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2211.09949","pdf_url":"https://arxiv.org/pdf/2211.09949","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309582373.pdf","grobid_xml":"https://content.openalex.org/works/W4309582373.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2973049979","https://openalex.org/W2972943112","https://openalex.org/W3209059054","https://openalex.org/W2407386500","https://openalex.org/W3203140070","https://openalex.org/W4297841557","https://openalex.org/W4224821750","https://openalex.org/W4385823023","https://openalex.org/W4392908918","https://openalex.org/W3038012435","https://openalex.org/W3035030897","https://openalex.org/W4206375145","https://openalex.org/W4375869065","https://openalex.org/W4385823417","https://openalex.org/W4406461695","https://openalex.org/W4416800207","https://openalex.org/W4402112601","https://openalex.org/W4391021746","https://openalex.org/W2946794439","https://openalex.org/W2058641082","https://openalex.org/W3197580070","https://openalex.org/W3209984917","https://openalex.org/W3168545914"],"related_works":["https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093","https://openalex.org/W2104490101","https://openalex.org/W3030709726","https://openalex.org/W2966487450","https://openalex.org/W2612632602","https://openalex.org/W2321805087","https://openalex.org/W624280404"],"abstract_inverted_index":{"Transformer-based":[0],"self-supervised":[1,66],"models":[2],"have":[3,28],"achieved":[4],"remarkable":[5],"success":[6],"in":[7],"speech":[8,67],"processing,":[9],"but":[10],"their":[11,39],"large":[12],"size":[13],"and":[14,62,81,104],"high":[15],"inference":[16],"cost":[17],"present":[18],"significant":[19],"challenges":[20],"for":[21,115],"real-world":[22],"deployment.":[23,116],"While":[24],"numerous":[25],"compression":[26,53,97,114],"techniques":[27],"been":[29],"proposed,":[30],"inconsistent":[31],"evaluation":[32],"metrics":[33],"make":[34],"it":[35],"difficult":[36],"to":[37],"compare":[38],"practical":[40,111],"effectiveness.":[41],"In":[42,92],"this":[43],"work,":[44],"we":[45,94],"conduct":[46],"a":[47],"comprehensive":[48],"study":[49],"of":[50],"four":[51],"common":[52],"methods,":[54],"including":[55],"weight":[56],"pruning,":[57,59],"head":[58],"low-rank":[60],"approximation,":[61],"knowledge":[63],"distillation":[64],"on":[65,113],"Transformers.":[68],"We":[69],"evaluate":[70],"each":[71,87],"method":[72,88],"under":[73,106],"three":[74],"key":[75],"metrics:":[76],"parameter":[77],"count,":[78],"multiply-accumulate":[79],"operations,":[80],"real-time":[82],"factor.":[83],"Results":[84],"show":[85],"that":[86],"offers":[89],"distinct":[90],"advantages.":[91],"addition,":[93],"contextualize":[95],"recent":[96],"techniques,":[98],"comparing":[99],"DistilHuBERT,":[100],"FitHuBERT,":[101],"LightHuBERT,":[102],"ARMHuBERT,":[103],"STaRHuBERT":[105],"the":[107],"same":[108],"framework,":[109],"offering":[110],"guidance":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2022-11-28T00:00:00"}