{"id":"https://openalex.org/W4297841786","doi":"https://doi.org/10.21437/interspeech.2022-10582","title":"Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition","display_name":"Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841786","doi":"https://doi.org/10.21437/interspeech.2022-10582"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10582","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.00169","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045908116","display_name":"Jash Rathod","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jash Rathod","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067313233","display_name":"Nauman Dawalatabad","orcid":"https://orcid.org/0000-0003-1592-6300"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nauman Dawalatabad","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079810318","display_name":"Shatrughan Singh","orcid":"https://orcid.org/0000-0003-3758-3214"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"SHATRUGHAN SINGH","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045908116"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":0.416,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.58431373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1691","last_page":"1695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9901000261306763,"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/T10860","display_name":"Speech and Audio Processing","score":0.9836999773979187,"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/encoder","display_name":"Encoder","score":0.7138048410415649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7123986482620239},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5724261403083801},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5106838345527649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5007317066192627},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.43856608867645264},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.42558518052101135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3388674259185791},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25137466192245483},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.18109455704689026},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0993257462978363}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7138048410415649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123986482620239},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5724261403083801},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5106838345527649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5007317066192627},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.43856608867645264},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42558518052101135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3388674259185791},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25137466192245483},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.18109455704689026},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0993257462978363},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10582","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"},{"id":"pmh:oai:arXiv.org:2210.00169","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.00169","pdf_url":"https://arxiv.org/pdf/2210.00169","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.00169","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.00169","pdf_url":"https://arxiv.org/pdf/2210.00169","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2095705004","https://openalex.org/W2233116163","https://openalex.org/W2293634267","https://openalex.org/W2508418541","https://openalex.org/W2540787960","https://openalex.org/W2750784772","https://openalex.org/W2754084392","https://openalex.org/W2783538964","https://openalex.org/W2885195348","https://openalex.org/W2936774411","https://openalex.org/W2952787292","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2963736842","https://openalex.org/W2973122799","https://openalex.org/W2975429091","https://openalex.org/W2978017171","https://openalex.org/W2997006708","https://openalex.org/W2997454826","https://openalex.org/W3007528493","https://openalex.org/W3008587939","https://openalex.org/W3015194534","https://openalex.org/W3033411150","https://openalex.org/W3034368386","https://openalex.org/W3095867028","https://openalex.org/W3097777922","https://openalex.org/W3125815078","https://openalex.org/W3163600291","https://openalex.org/W4210435435","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2117438306","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W2004297762","https://openalex.org/W2351972135","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"The":[0],"smaller":[1,10,19,42,68],"memory":[2],"bandwidth":[3],"in":[4,49,94,100,139,161],"smart":[5],"devices":[6],"prompts":[7],"development":[8],"of":[9],"Automatic":[11],"Speech":[12],"Recognition":[13],"(ASR)":[14],"models.":[15],"To":[16],"obtain":[17],"a":[18,32,60,67,105,116,140],"model,":[20],"one":[21],"can":[22],"employ":[23,104],"the":[24,50,73,89,112,122,135,162,166],"model":[25,34,43,51,65,125,133,138],"compression":[26,35,153],"techniques.":[27],"Knowledge":[28],"distillation":[29],"(KD)":[30],"is":[31,57],"popular":[33],"approach":[36,119],"that":[37],"has":[38],"shown":[39,79],"to":[40,66,80,120,165],"achieve":[41],"size":[44,63,69],"with":[45,109,134],"relatively":[46],"lesser":[47],"degradation":[48,160],"performance.":[52],"In":[53],"this":[54,101],"approach,":[55],"knowledge":[56],"distilled":[58,136],"from":[59],"trained":[61],"large":[62],"teacher":[64,132,168],"student":[70,137],"model.":[71,169],"Also,":[72],"transducer":[74,107,124],"based":[75],"models":[76,91],"have":[77,150],"recently":[78],"perform":[81],"well":[82],"for":[83],"on-device":[84],"streaming":[85,106],"ASR":[86],"task,":[87],"while":[88],"conformer":[90,110,123],"are":[92],"efficient":[93],"handling":[95],"long":[96],"term":[97],"dependencies.":[98],"Hence":[99],"work":[102],"we":[103],"architecture":[108],"as":[111],"encoder.":[113],"We":[114,128],"propose":[115],"multi-stage":[117,141],"progressive":[118],"compress":[121],"using":[126],"KD.":[127],"progressively":[129],"update":[130],"our":[131,147],"setup.":[142],"On":[143],"standard":[144],"LibriSpeech":[145],"dataset,":[146],"experimental":[148],"results":[149],"successfully":[151],"achieved":[152],"rates":[154],"greater":[155],"than":[156],"60%":[157],"without":[158],"significant":[159],"performance":[163],"compared":[164],"larger":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}