{"id":"https://openalex.org/W3163522772","doi":"https://doi.org/10.1109/icassp39728.2021.9413762","title":"Generalized Knowledge Distillation from an Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering","display_name":"Generalized Knowledge Distillation from an Ensemble of Specialized Teachers Leveraging Unsupervised Neural Clustering","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163522772","doi":"https://doi.org/10.1109/icassp39728.2021.9413762","mag":"3163522772"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102876935","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0002-4601-0955"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["IBM Research AI, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, JAPAN","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research AI, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, JAPAN","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"6868","last_page":"6872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7385145425796509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736929178237915},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6639034748077393},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6298606395721436},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5529739856719971},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.534182071685791},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5318275094032288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48574763536453247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47132256627082825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45154544711112976},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4141346216201782},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11870834231376648},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1108052134513855}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7385145425796509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736929178237915},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6639034748077393},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6298606395721436},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5529739856719971},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.534182071685791},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5318275094032288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48574763536453247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47132256627082825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45154544711112976},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4141346216201782},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11870834231376648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1108052134513855},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W184194209","https://openalex.org/W1571931074","https://openalex.org/W1602122992","https://openalex.org/W1904457459","https://openalex.org/W2097978681","https://openalex.org/W2110765229","https://openalex.org/W2120773360","https://openalex.org/W2134797427","https://openalex.org/W2136933783","https://openalex.org/W2173379916","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2402040300","https://openalex.org/W2508418541","https://openalex.org/W2512865187","https://openalex.org/W2747909401","https://openalex.org/W2883725317","https://openalex.org/W2910715461","https://openalex.org/W2911629330","https://openalex.org/W2913178639","https://openalex.org/W2950180292","https://openalex.org/W2963376890","https://openalex.org/W2963726581","https://openalex.org/W2963927463","https://openalex.org/W2973094317","https://openalex.org/W3008987902","https://openalex.org/W3095799548","https://openalex.org/W4293871399","https://openalex.org/W6634380342","https://openalex.org/W6639829665","https://openalex.org/W6674334065","https://openalex.org/W6679909955","https://openalex.org/W6680549991","https://openalex.org/W6685316698","https://openalex.org/W6697339895","https://openalex.org/W6712847557","https://openalex.org/W6753000030"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W2542937328","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W4360952157","https://openalex.org/W4220731478","https://openalex.org/W2069409835","https://openalex.org/W2153647085"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"improved":[4],"generalized":[5,121],"knowledge":[6,148],"distillation":[7,149],"framework":[8],"with":[9,58,83,124],"multiple":[10,84,140],"dissimilar":[11],"teacher":[12,114,122],"networks,":[13],"each":[14,65],"of":[15,51,93,111,163],"which":[16],"is":[17,80,167],"specialized":[18,85,113],"for":[19,48],"a":[20,25,41,72,100,108,112,120,125,143],"specific":[21],"domain,":[22],"to":[23,31,43,116,135],"make":[24],"deployable":[26],"student":[27,74,95,145],"network":[28,75,96,146],"more":[29],"robust":[30],"challenging":[32,175],"acoustic":[33,66],"environments.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,69,133],"first":[39],"address":[40],"method":[42],"partition":[44],"the":[45,52,88,91,94,137,158,164],"training":[46,89],"data":[47,79,127],"constructing":[49],"ensembles":[50],"teachers":[53],"from":[54,77,107,139],"unsupervised":[55],"neural":[56],"clustering":[57],"features":[59],"based":[60],"on":[61,169],"context-dependent":[62],"phonemes":[63],"representing":[64],"domain.":[67],"Second,":[68],"illustrate":[70],"how":[71],"single":[73,144],"designed":[76],"partitioned":[78],"effectively":[81],"trained":[82,123],"teachers.":[86],"During":[87],"step,":[90],"weights":[92],"are":[97],"updated":[98],"using":[99],"composite":[101],"two-part":[102],"cross":[103],"entropy":[104],"loss":[105],"obtained":[106],"pair":[109],"consisting":[110],"corresponding":[115],"input":[117],"speech":[118],"and":[119],"balanced":[126],"set.":[128],"Unlike":[129],"system":[130],"combination":[131],"methods,":[132],"aim":[134],"incorporate":[136],"benefits":[138],"models":[141],"into":[142],"via":[147],"that":[150],"does":[151],"not":[152],"increase":[153],"any":[154],"computational":[155],"costs":[156],"during":[157],"decoding":[159],"time.":[160],"The":[161],"improvement":[162],"proposed":[165],"technique":[166],"shown":[168],"acoustically":[170],"diverse":[171],"signals":[172],"contaminated":[173],"by":[174],"practical":[176],"noises.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}