{"id":"https://openalex.org/W3172442681","doi":"https://doi.org/10.21437/interspeech.2021-354","title":"Collaborative Training of Acoustic Encoders for Speech Recognition","display_name":"Collaborative Training of Acoustic Encoders for Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3172442681","doi":"https://doi.org/10.21437/interspeech.2021-354","mag":"3172442681"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-354","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.08960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034208747","display_name":"Varun Nagaraja","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Varun Nagaraja","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104363400","display_name":"Ganesh Venkatesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganesh Venkatesh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016704219","display_name":"Vikas Chandra","orcid":"https://orcid.org/0009-0005-4996-8455"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikas Chandra","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034208747"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07566483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4573","last_page":"4577"},"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":0.9997000098228455,"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":0.9990000128746033,"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":0.7977150678634644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7691186666488647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7043915390968323},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6301673650741577},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6256717443466187},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5808276534080505},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48610472679138184},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44336998462677},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44014376401901245},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2216203510761261},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09568801522254944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08792299032211304}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7977150678634644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691186666488647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7043915390968323},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6301673650741577},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6256717443466187},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5808276534080505},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48610472679138184},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44336998462677},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44014376401901245},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2216203510761261},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09568801522254944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08792299032211304},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-354","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.08960","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08960","pdf_url":"https://arxiv.org/pdf/2106.08960","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3172442681","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.08960v2","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.08960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.08960","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.08960","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08960","pdf_url":"https://arxiv.org/pdf/2106.08960","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3172442681.pdf","grobid_xml":"https://content.openalex.org/works/W3172442681.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2407080277","https://openalex.org/W2508418541","https://openalex.org/W2620998106","https://openalex.org/W2680270903","https://openalex.org/W2767421475","https://openalex.org/W2884751099","https://openalex.org/W2889129739","https://openalex.org/W2911629330","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2963250244","https://openalex.org/W2963373431","https://openalex.org/W2963376890","https://openalex.org/W2963393494","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963736842","https://openalex.org/W2963766446","https://openalex.org/W2963927126","https://openalex.org/W2964038834","https://openalex.org/W2964220233","https://openalex.org/W2981698279","https://openalex.org/W3008008574","https://openalex.org/W3008525923","https://openalex.org/W3016010032","https://openalex.org/W3035321581","https://openalex.org/W3096888553","https://openalex.org/W3097777922","https://openalex.org/W3128478537","https://openalex.org/W3144557079","https://openalex.org/W3149509723","https://openalex.org/W3162309234","https://openalex.org/W3162649911","https://openalex.org/W3162665866","https://openalex.org/W3177024751"],"related_works":["https://openalex.org/W3197201410","https://openalex.org/W2169813781","https://openalex.org/W2914151612","https://openalex.org/W2586425531","https://openalex.org/W1495019370","https://openalex.org/W2792156659","https://openalex.org/W2337627957","https://openalex.org/W3016010944","https://openalex.org/W3041561163","https://openalex.org/W2922358226","https://openalex.org/W3031135612","https://openalex.org/W3109079702","https://openalex.org/W3021188327","https://openalex.org/W2964012862","https://openalex.org/W3143797047","https://openalex.org/W3091830790","https://openalex.org/W3140783160","https://openalex.org/W3179150334","https://openalex.org/W2914445497","https://openalex.org/W2607361225"],"abstract_inverted_index":{"On-device":[0],"speech":[1,68],"recognition":[2],"requires":[3],"training":[4,26,39,50,61],"models":[5],"of":[6,32,64],"different":[7,20,65,77],"sizes":[8,66],"for":[9,59,67,99],"deploying":[10],"on":[11,137],"devices":[12],"with":[13,105],"various":[14],"computational":[15],"budgets.":[16],"When":[17],"building":[18],"such":[19],"models,":[21],"we":[22],"can":[23,124],"benefit":[24],"from":[25],"them":[27],"jointly":[28],"to":[29,127],"take":[30],"advantage":[31],"the":[33,46,49,106,113,119,133,139],"knowledge":[34],"shared":[35],"between":[36],"them.":[37],"Joint":[38],"is":[40],"also":[41,91],"efficient":[42],"since":[43],"it":[44],"reduces":[45],"redundancy":[47],"in":[48,132],"procedure's":[51],"data":[52],"handling":[53],"operations.":[54],"We":[55,70,109],"propose":[56],"a":[57,72,81,128],"method":[58],"collaboratively":[60,120],"acoustic":[62,78,88,122],"encoders":[63,79,89,123],"recognition.":[69],"use":[71],"sequence":[73],"transducer":[74,107],"setup":[75],"where":[76],"share":[80],"common":[82],"predictor":[83],"and":[84,116],"joiner":[85],"modules.":[86],"The":[87],"are":[90],"trained":[92,121],"using":[93,112],"co-distillation":[94],"through":[95],"an":[96],"auxiliary":[97],"task":[98],"frame":[100],"level":[101],"chenone":[102],"prediction,":[103],"along":[104],"loss.":[108],"perform":[110],"experiments":[111],"LibriSpeech":[114],"corpus":[115],"demonstrate":[117],"that":[118],"provide":[125],"up":[126],"11%":[129],"relative":[130],"improvement":[131],"word":[134],"error":[135],"rate":[136],"both":[138],"test":[140],"partitions.":[141]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}