{"id":"https://openalex.org/W4224821750","doi":"https://doi.org/10.21437/interspeech.2022-10269","title":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","display_name":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224821750","doi":"https://doi.org/10.21437/interspeech.2022-10269"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10269","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10269","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5100431267","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-5211-2114"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065778847","display_name":"Qibing Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibing Bai","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077069016","display_name":"Junyi Ao","orcid":"https://orcid.org/0000-0001-8979-0835"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Ao","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong (Shenzhen)"],"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong (Shenzhen)","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Long Zhou","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044413617","display_name":"Zhixiang Xiong","orcid":"https://orcid.org/0009-0005-7987-0870"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiang Xiong","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004301353","display_name":"Zhihua Wei","orcid":"https://orcid.org/0000-0002-5937-3907"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Wei","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433403","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-7298-1694"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Peng Cheng Laboratory","Department of Computer Science and Engineering, Southern University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong (Shenzhen)"],"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong (Shenzhen)","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100431267"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":4.173,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95341812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1686","last_page":"1690"},"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":0.9904999732971191,"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":0.9896000027656555,"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":0.772939145565033},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5289937257766724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5160040855407715},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5005900859832764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3670870065689087},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3440430164337158},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06404942274093628},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.06235694885253906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772939145565033},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5289937257766724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5160040855407715},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5005900859832764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3670870065689087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3440430164337158},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06404942274093628},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.06235694885253906},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10269","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10269","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G23458378","display_name":null,"funder_award_id":"61976160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5036809106","display_name":null,"funder_award_id":"62076182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5387966317","display_name":null,"funder_award_id":"61906137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5686205310","display_name":null,"funder_award_id":"62076184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8264781341","display_name":null,"funder_award_id":"61976158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2915589364","https://openalex.org/W2933138175","https://openalex.org/W2963425185","https://openalex.org/W2978017171","https://openalex.org/W2994749257","https://openalex.org/W2995181338","https://openalex.org/W2997666887","https://openalex.org/W3000280594","https://openalex.org/W3012561096","https://openalex.org/W3015609966","https://openalex.org/W3024880312","https://openalex.org/W3036601975","https://openalex.org/W3096109555","https://openalex.org/W3096485810","https://openalex.org/W3167851353","https://openalex.org/W3169320628","https://openalex.org/W3197580070","https://openalex.org/W3204801262","https://openalex.org/W3209984917","https://openalex.org/W3215290109","https://openalex.org/W4206375145","https://openalex.org/W4221145109","https://openalex.org/W4225547403","https://openalex.org/W4226033575","https://openalex.org/W4226075153","https://openalex.org/W4226484461","https://openalex.org/W4281401280","https://openalex.org/W4287121455","https://openalex.org/W4287374065","https://openalex.org/W4304206546","https://openalex.org/W4308349017"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W2371343292","https://openalex.org/W2062195135","https://openalex.org/W629290331","https://openalex.org/W617685022","https://openalex.org/W1509983653","https://openalex.org/W3215563689","https://openalex.org/W610590827","https://openalex.org/W591599671","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,10,79],"representation":[2],"learning":[3],"has":[4],"shown":[5],"promising":[6],"results":[7],"in":[8,130,145],"various":[9],"processing":[11],"tasks.However,":[12],"the":[13,41,71,83,87,96,110,120,127],"pre-trained":[14,165],"models,":[15],"e.g.,":[16,149],"HuBERT,":[17],"are":[18,167],"storage-intensive":[19],"Transformers,":[20],"limiting":[21],"their":[22],"scope":[23],"of":[24,60,136],"applications":[25],"under":[26],"lowresource":[27],"settings.To":[28],"this":[29],"end,":[30],"we":[31,50],"propose":[32],"LightHuBERT,":[33],"a":[34,52,65,134,141,159],"once-for-all":[35],"Transformer":[36],"compression":[37,143],"framework,":[38],"to":[39,69,126],"find":[40],"desired":[42],"architectures":[43,94],"automatically":[44],"by":[45],"pruning":[46],"structured":[47],"parameters.More":[48],"precisely,":[49],"create":[51],"Transformer-based":[53],"supernet":[54],"that":[55],"is":[56],"nested":[57],"with":[58,119,133,158],"thousands":[59],"weight-sharing":[61],"subnets":[62],"and":[63,82,106,115,139,155,164],"design":[64],"two-stage":[66],"distillation":[67],"strategy":[68],"leverage":[70],"contextualized":[72],"latent":[73],"representations":[74],"from":[75],"HuBERT.Experiments":[76],"on":[77,113],"automatic":[78,150],"recognition":[80],"(ASR)":[81],"SU-PERB":[84],"benchmark":[85],"show":[86],"proposed":[88],"LightHuBERT":[89],"enables":[90],"over":[91],"10":[92],"9":[93],"concerning":[95],"embedding":[97],"dimension,":[98,100],"attention":[99],"head":[101],"number,":[102],"feed-forward":[103],"network":[104,107],"ratio,":[105],"depth.LightHuBERT":[108],"outperforms":[109],"original":[111],"HuBERT":[112],"ASR":[114],"five":[116],"SUPERB":[117,147],"tasks":[118,132],"Hu-BERT":[121],"size,":[122],"achieves":[123],"comparable":[124],"performance":[125],"teacher":[128],"model":[129],"most":[131],"reduction":[135],"29%":[137],"parameters,":[138],"obtains":[140],"3.5\u00d7":[142],"ratio":[144],"three":[146],"tasks,":[148],"speaker":[151],"verification,":[152],"keyword":[153],"spotting,":[154],"intent":[156],"classification,":[157],"slight":[160],"accuracy":[161],"loss.The":[162],"code":[163],"models":[166],"available":[168],"at":[169],"https://github.com/mechanicalsea/lighthubert.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}