{"id":"https://openalex.org/W7148489675","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/W7148489675","doi":"https://doi.org/10.1109/asru65441.2025.11434686"},"language":null,"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":"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/A5113755224","display_name":"T. W. 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":true,"raw_author_name":"Tzu-Quan Lin","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"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/A5132751855","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"],"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"],"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"],"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"],"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/A5132807525","display_name":"Hung-Yi Lee","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":"Hung-Yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"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/A5132789106","display_name":"Hao Tang","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":"Hao Tang","raw_affiliation_strings":["University of Edinburgh,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113755224"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87571307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.652999997138977,"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":0.652999997138977,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.12139999866485596,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.02250000089406967,"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/transformer","display_name":"Transformer","score":0.4821000099182129},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30169999599456787},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2994999885559082},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.2971999943256378},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.2935999929904938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5756000280380249},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4821000099182129},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.288100004196167},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2058641082","https://openalex.org/W2407386500","https://openalex.org/W2946794439","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W3035030897","https://openalex.org/W3038012435","https://openalex.org/W3168545914","https://openalex.org/W3197580070","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206375145","https://openalex.org/W4224821750","https://openalex.org/W4297841557","https://openalex.org/W4375869065","https://openalex.org/W4385823023","https://openalex.org/W4385823417","https://openalex.org/W4391021746","https://openalex.org/W4392908918","https://openalex.org/W4402112601","https://openalex.org/W4406461695","https://openalex.org/W4416800207"],"related_works":[],"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":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}