{"id":"https://openalex.org/W4319862463","doi":"https://doi.org/10.1109/slt54892.2023.10023326","title":"An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition","display_name":"An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862463","doi":"https://doi.org/10.1109/slt54892.2023.10023326"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023326","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":"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/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Georgia Institute of Technology,USA","Amazon Alexa AI, USA","Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605612","display_name":"I\u2010Ming Chen","orcid":"https://orcid.org/0000-0002-4831-3781"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Fan Chen","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["NO","US"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Georgia Institute of Technology,USA","Georgia Institute of Technology, USA","Department of Electronic Systems, NTNU, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Department of Electronic Systems, NTNU, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,USA","Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020376803"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.2261,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.35137949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1074","last_page":"1080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9818000197410583,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9661999940872192,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7942616939544678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6494787335395813},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6470462679862976},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5442358255386353},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49507060647010803},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44808804988861084},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.44280073046684265},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4340170919895172},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4309147298336029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36339956521987915},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3083643317222595},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10441392660140991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942616939544678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6494787335395813},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6470462679862976},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5442358255386353},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49507060647010803},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44808804988861084},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.44280073046684265},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4340170919895172},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4309147298336029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36339956521987915},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3083643317222595},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10441392660140991},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt54892.2023.10023326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023326","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"},{"id":"pmh:oai:iris.unipa.it:10447/636665","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/636665","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"},{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2048673468","https://openalex.org/W2051267297","https://openalex.org/W2061533153","https://openalex.org/W2084514013","https://openalex.org/W2109426455","https://openalex.org/W2127141656","https://openalex.org/W2128970689","https://openalex.org/W2148154194","https://openalex.org/W2167372639","https://openalex.org/W2186926886","https://openalex.org/W2293829681","https://openalex.org/W2327501763","https://openalex.org/W2473418344","https://openalex.org/W2508418541","https://openalex.org/W2526425061","https://openalex.org/W2594311007","https://openalex.org/W2690039764","https://openalex.org/W2806521799","https://openalex.org/W2896422817","https://openalex.org/W2962826786","https://openalex.org/W3025567392","https://openalex.org/W3161932608","https://openalex.org/W3162072286","https://openalex.org/W3173081491","https://openalex.org/W3198781161","https://openalex.org/W4210970267","https://openalex.org/W4224934172","https://openalex.org/W4225262970","https://openalex.org/W4226302796","https://openalex.org/W4226316089","https://openalex.org/W4226418308","https://openalex.org/W6638749077","https://openalex.org/W6686739807","https://openalex.org/W6728897251","https://openalex.org/W6747732332","https://openalex.org/W6760226272"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W1566315437","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W2594897229","https://openalex.org/W4221142855"],"abstract_inverted_index":{"Differential":[0],"privacy":[1,22,45],"(DP)":[2],"is":[3],"one":[4],"data":[5,95],"protection":[6],"avenue":[7],"to":[8,42,57,77],"safeguard":[9],"user":[10],"information":[11],"used":[12],"for":[13,144,159],"training":[14],"deep":[15,104],"models":[16,123],"by":[17,68],"imposing":[18],"noisy":[19],"distortion":[20],"on":[21,113,161],"data.":[23],"Such":[24],"a":[25,31,44,87,155],"noise":[26,65],"perturbation":[27],"often":[28],"results":[29],"in":[30,35,40,97],"severe":[32],"performance":[33],"degradation":[34],"automatic":[36],"speech":[37,83,163],"recognition":[38],"(ASR)":[39],"order":[41],"meet":[43],"budget":[46],"\u03b5.":[47,72],"Private":[48],"aggregation":[49],"of":[50,71],"teacher":[51],"ensemble":[52,55],"(PATE)":[53],"utilizes":[54],"probabilities":[56],"improve":[58],"ASR":[59,98,122,157],"accuracy":[60],"when":[61],"dealing":[62],"with":[63,79,150],"the":[64,114,125],"effects":[66],"controlled":[67],"small":[69],"values":[70],"We":[73,100,152],"extend":[74],"PATE":[75,120],"learning":[76],"work":[78],"dynamic":[80],"patterns,":[81],"namely":[82],"utterances,":[84],"and":[85,110,117,142],"perform":[86],"first":[88],"experimental":[89],"demonstration":[90],"that":[91],"it":[92],"prevents":[93],"acoustic":[94],"leakage":[96],"training.":[99],"evaluate":[101],"three":[102],"end-to-end":[103],"models,":[105],"including":[106],"LAS,":[107],"hybrid":[108],"CTC/attention,":[109],"RNN":[111,146],"transducer,":[112],"open-source":[115],"LibriSpeech":[116],"TIMIT":[118],"corpora.":[119,164],"learning-enhanced":[121],"outperform":[124],"benchmark":[126],"DP-SGD":[127],"mechanisms,":[128],"especially":[129],"under":[130],"strict":[131],"DP":[132],"budgets,":[133],"giving":[134],"relative":[135],"word":[136],"error":[137],"rate":[138],"reductions":[139],"between":[140],"26.2%":[141],"27.5%":[143],"an":[145],"transducer":[147],"model":[148],"evaluated":[149],"LibriSpeech.":[151],"also":[153],"introduce":[154],"DP-preserving":[156],"solution":[158],"pretraining":[160],"public":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"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"}