{"id":"https://openalex.org/W4375869065","doi":"https://doi.org/10.1109/icassp49357.2023.10095780","title":"Structured Pruning of Self-Supervised Pre-Trained Models for Speech Recognition and Understanding","display_name":"Structured Pruning of Self-Supervised Pre-Trained Models for Speech Recognition and Understanding","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869065","doi":"https://doi.org/10.1109/icassp49357.2023.10095780"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"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":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074393700","display_name":"Felix Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","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,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7608839273452759},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6940068602561951},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6911234855651855},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6323597431182861},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5290882587432861},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5178206562995911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4991135597229004},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4472110867500305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43295663595199585},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42803120613098145},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.42716148495674133},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42649537324905396},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4101408123970032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3693777322769165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.31969526410102844},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15169480443000793},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06649813055992126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608839273452759},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6940068602561951},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6911234855651855},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6323597431182861},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5290882587432861},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5178206562995911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4991135597229004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4472110867500305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43295663595199585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42803120613098145},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.42716148495674133},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42649537324905396},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4101408123970032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693777322769165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31969526410102844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15169480443000793},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06649813055992126},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W2127141656","https://openalex.org/W2250357346","https://openalex.org/W2460144244","https://openalex.org/W2899663614","https://openalex.org/W2945886900","https://openalex.org/W2962851801","https://openalex.org/W2962965870","https://openalex.org/W2963828549","https://openalex.org/W2972584841","https://openalex.org/W2978017171","https://openalex.org/W2979691890","https://openalex.org/W3036601975","https://openalex.org/W3091900426","https://openalex.org/W3100460087","https://openalex.org/W3105966348","https://openalex.org/W3142589538","https://openalex.org/W3163105696","https://openalex.org/W3176647794","https://openalex.org/W3197580070","https://openalex.org/W3200129129","https://openalex.org/W3203140070","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3217767527","https://openalex.org/W4206375145","https://openalex.org/W4224821750","https://openalex.org/W4224933800","https://openalex.org/W4226103796","https://openalex.org/W4226126941","https://openalex.org/W4281492411","https://openalex.org/W4283700140","https://openalex.org/W4284973286","https://openalex.org/W4287121455","https://openalex.org/W4295312788","https://openalex.org/W4297841557","https://openalex.org/W4297841903","https://openalex.org/W4319862410","https://openalex.org/W4372270126","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6691509046","https://openalex.org/W6726275242","https://openalex.org/W6739901393","https://openalex.org/W6745499552","https://openalex.org/W6755977528","https://openalex.org/W6766978945","https://openalex.org/W6768851824","https://openalex.org/W6780218876","https://openalex.org/W6796551075","https://openalex.org/W6839026989","https://openalex.org/W6839423864","https://openalex.org/W6846714717","https://openalex.org/W6850036870"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,49],"representation":[2,73],"learning":[3],"(SSL)":[4],"has":[5,77],"shown":[6],"to":[7,29,96,121,128,134],"be":[8],"effective":[9],"in":[10,38],"various":[11],"downstream":[12],"tasks,":[13],"but":[14,59,81],"SSL":[15],"models":[16,50],"are":[17],"usually":[18],"large":[19],"and":[20,34,105,125],"slow.":[21],"Model":[22],"compression":[23],"techniques":[24],"such":[25,99],"as":[26],"pruning":[27,45,94],"aim":[28],"reduce":[30,129],"the":[31,44,109,116,130],"model":[32],"size":[33,80],"computation":[35,131],"without":[36,136],"degradation":[37],"accuracy.":[39],"Prior":[40],"studies":[41],"focus":[42],"on":[43,66,103],"of":[46,56],"Transformers;":[47],"however,":[48],"not":[51],"only":[52],"utilize":[53],"a":[54,62,78,82],"stack":[55],"Transformer":[57],"blocks,":[58],"also":[60],"combine":[61],"frontend":[63,76],"network":[64],"based":[65],"multiple":[67],"convolutional":[68],"layers":[69],"for":[70],"low-level":[71],"feature":[72],"learning.":[74],"This":[75],"small":[79],"heavy":[83],"computational":[84],"cost.":[85],"In":[86],"this":[87],"work,":[88],"we":[89],"propose":[90],"three":[91],"task-specific":[92],"structured":[93],"methods":[95],"deal":[97],"with":[98,119],"heterogeneous":[100],"networks.":[101],"Experiments":[102],"LibriSpeech":[104],"SLURP":[106],"show":[107],"that":[108],"proposed":[110],"method":[111],"is":[112,126],"more":[113],"accurate":[114],"than":[115],"original":[117],"wav2vec2-base":[118],"10%":[120],"30%":[122],"less":[123],"computation,":[124],"able":[127],"by":[132],"40%":[133],"50%":[135],"any":[137],"degradation.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}