{"id":"https://openalex.org/W4210435435","doi":"https://doi.org/10.1109/asru51503.2021.9688121","title":"Two-Pass End-to-End ASR Model Compression","display_name":"Two-Pass End-to-End ASR Model Compression","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210435435","doi":"https://doi.org/10.1109/asru51503.2021.9688121"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688121","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 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/A5067313233","display_name":"Nauman Dawalatabad","orcid":"https://orcid.org/0000-0003-1592-6300"},"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":"Nauman Dawalatabad","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013247471","display_name":"Tushar Vatsal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tushar Vatsal","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069263468","display_name":"Ashutosh Gupta","orcid":"https://orcid.org/0000-0002-3622-1740"},"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":"Ashutosh Gupta","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340036","display_name":"Sung-Soo Kim","orcid":"https://orcid.org/0000-0003-3207-4648"},"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":"Sungsoo Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"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":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5067313233"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53552066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"403","last_page":"410"},"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":0.9988999962806702,"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":0.9979000091552734,"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":0.8348634839057922},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7365956902503967},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6104484796524048},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5933499336242676},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5852851867675781},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5429352521896362},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.45753055810928345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42389488220214844},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.41644757986068726},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19311735033988953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348634839057922},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7365956902503967},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6104484796524048},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5933499336242676},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5852851867675781},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5429352521896362},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.45753055810928345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42389488220214844},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.41644757986068726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19311735033988953},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688121","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2507699225","https://openalex.org/W2508418541","https://openalex.org/W2540787960","https://openalex.org/W2747909401","https://openalex.org/W2767487732","https://openalex.org/W2789876780","https://openalex.org/W2799800213","https://openalex.org/W2885195348","https://openalex.org/W2892008152","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2963736842","https://openalex.org/W2973122799","https://openalex.org/W2997454826","https://openalex.org/W3007528493","https://openalex.org/W3008587939","https://openalex.org/W3034368386","https://openalex.org/W3095867028","https://openalex.org/W3096518646","https://openalex.org/W3138154797","https://openalex.org/W3162649911","https://openalex.org/W3163600291","https://openalex.org/W3168212167","https://openalex.org/W3168770049","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6638575559","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6674330103","https://openalex.org/W6696934422","https://openalex.org/W6739901393","https://openalex.org/W6743155827","https://openalex.org/W6745801839","https://openalex.org/W6784765489","https://openalex.org/W6785501301"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W2160451571","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,36],"on":[2,38,163],"smart":[3],"devices":[4,40],"is":[5],"challenging":[6],"owing":[7],"to":[8,31,71,115,186],"the":[9,21,43,73,76,93,98,117,125,137,147,183,187],"small":[10,14,39],"memory":[11],"footprint.":[12],"Hence":[13],"size":[15,74],"ASR":[16],"models":[17,37],"are":[18],"desirable.":[19],"With":[20],"use":[22,102],"of":[23,75,177],"popular":[24,85],"transducer-based":[25],"models,":[26],"it":[27],"has":[28,52],"become":[29],"possible":[30],"practically":[32],"deploy":[33],"streaming":[34,57],"speech":[35,59],"[1].":[41],"Recently,":[42],"two-pass":[44,77,188],"model":[45,78,106,110,135,149],"[2]":[46],"combining":[47],"RNN-T":[48,105,119,153,155],"and":[49,68,111,128,157],"LAS":[50,131,158],"modules":[51],"shown":[53],"exceptional":[54],"performance":[55],"for":[56,79,133,146],"on-device":[58],"recognition.":[60],"In":[61,97],"this":[62],"work,":[63],"we":[64,101,143],"propose":[65],"a":[66,84,103,108,130,151,173],"simple":[67],"effective":[69],"approach":[70,88],"reduce":[72],"memory-constrained":[80],"devices.":[81],"We":[82],"employ":[83],"knowledge":[86,113],"distillation":[87,114],"in":[89,182],"three":[90],"stages":[91],"using":[92,136],"Teacher-Student":[94],"training":[95],"technique.":[96],"first":[99],"stage,":[100],"trained":[104,138],"as":[107],"teacher":[109,140,189],"perform":[112,144],"train":[116],"student":[118,134,148],"model.":[120,141,190],"The":[121],"second":[122],"stage":[123],"uses":[124],"shared":[126,152],"encoder":[127],"trains":[129],"rescorer":[132],"RNN-T+LAS":[139],"Finally,":[142],"deep-finetuning":[145],"with":[150],"encoder,":[154],"decoder,":[156],"rescorer.":[159],"Our":[160],"experimental":[161],"results":[162],"standard":[164],"LibriSpeech":[165],"dataset":[166],"show":[167],"that":[168],"our":[169],"system":[170],"can":[171],"achieve":[172],"high":[174],"compression":[175],"rate":[176],"55%":[178],"without":[179],"significant":[180],"degradation":[181],"WER":[184],"compared":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}