{"id":"https://openalex.org/W4319862425","doi":"https://doi.org/10.1109/slt54892.2023.10022446","title":"Learning a Dual-Mode Speech Recognition Model VIA Self-Pruning","display_name":"Learning a Dual-Mode Speech Recognition Model VIA Self-Pruning","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862425","doi":"https://doi.org/10.1109/slt54892.2023.10022446"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022446","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022446","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":"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/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunxi Liu","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047358828","display_name":"Yuan Shangguan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Shangguan","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069376593","display_name":"Haichuan Yang","orcid":"https://orcid.org/0000-0001-7100-7945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haichuan Yang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039488725","display_name":"Raghuraman Krishnamoorthi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghuraman Krishnamoorthi","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"279"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.8827613592147827},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5877580046653748},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5731329917907715},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5209192633628845},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49700191617012024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4693794250488281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4543149471282959},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.42356234788894653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3586401641368866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8827613592147827},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5877580046653748},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5731329917907715},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5209192633628845},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49700191617012024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693794250488281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4543149471282959},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.42356234788894653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3586401641368866},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022446","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022446","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2138019504","https://openalex.org/W2407080277","https://openalex.org/W2805003733","https://openalex.org/W2908510526","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963925437","https://openalex.org/W2981857663","https://openalex.org/W2995181338","https://openalex.org/W3008898571","https://openalex.org/W3015194534","https://openalex.org/W3016010032","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3095311338","https://openalex.org/W3097777922","https://openalex.org/W3125815078","https://openalex.org/W3144557079","https://openalex.org/W3146505093","https://openalex.org/W3149509723","https://openalex.org/W3160766462","https://openalex.org/W3161873870","https://openalex.org/W3162309234","https://openalex.org/W3162665866","https://openalex.org/W3163203022","https://openalex.org/W3196835955","https://openalex.org/W3197478142","https://openalex.org/W3198492054","https://openalex.org/W3207326706","https://openalex.org/W3207629995","https://openalex.org/W4225307083","https://openalex.org/W4296068782","https://openalex.org/W6638749077","https://openalex.org/W6751979845","https://openalex.org/W6757817989","https://openalex.org/W6761305474","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6786300550","https://openalex.org/W6790121257","https://openalex.org/W6810734409"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W2770234245","https://openalex.org/W2566006169","https://openalex.org/W2987774938","https://openalex.org/W632915154","https://openalex.org/W4229499248","https://openalex.org/W4378874356","https://openalex.org/W2055733372","https://openalex.org/W2369811061","https://openalex.org/W3089997100"],"abstract_inverted_index":{"There":[0],"is":[1],"growing":[2],"interest":[3],"in":[4,33,65,75,99,131],"unifying":[5],"the":[6,23,37,62,125,140],"streaming":[7,38,89,143],"and":[8,26,46,92,116,134],"full-context":[9,58],"automatic":[10],"speech":[11],"recognition":[12],"(ASR)":[13],"networks":[14],"into":[15],"a":[16,85,93,100],"single":[17,77,101],"end-to-end":[18],"ASR":[19,35,39,90,118],"model":[20,24,128],"to":[21,82,138],"simplify":[22],"training":[25,109],"deployment":[27],"for":[28],"both":[29,111],"use":[30],"cases.":[31],"While":[32],"real-world":[34],"applications,":[36],"models":[40],"typically":[41],"operate":[42],"under":[43],"more":[44],"storage":[45],"computational":[47],"constraints":[48],"-":[49,54],"e.g.,":[50],"on":[51,110],"embedded":[52],"devices":[53],"than":[55],"any":[56],"server-side":[57],"models.":[59],"Motivated":[60],"by":[61],"recent":[63],"progress":[64],"Omni-sparsity":[66],"supernet":[67,108],"training,":[68],"where":[69],"multiple":[70],"subnetworks":[71],"are":[72],"jointly":[73,83],"optimized":[74],"one":[76],"model,":[78,91,98],"this":[79],"work":[80],"aims":[81],"learn":[84],"compact":[86,141],"sparse":[87,142],"on-device":[88],"large":[94,126],"dense":[95],"server":[96],"non-streaming":[97,127],"supernet.":[102],"Next,":[103],"we":[104],"present":[105],"that,":[106],"performing":[107],"wav2vec":[112],"2.0":[113],"self-supervised":[114],"learning":[115],"supervised":[117],"fine-tuning":[119],"can":[120],"not":[121],"only":[122],"substantially":[123],"improve":[124,139],"as":[129],"shown":[130],"prior":[132],"works,":[133],"also":[135],"be":[136],"able":[137],"model.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}