{"id":"https://openalex.org/W4375869224","doi":"https://doi.org/10.1109/icassp49357.2023.10096445","title":"Ensemble Knowledge Distillation of Self-Supervised Speech Models","display_name":"Ensemble Knowledge Distillation of Self-Supervised Speech Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869224","doi":"https://doi.org/10.1109/icassp49357.2023.10096445"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5112912495","display_name":"Kuan -Po Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kuan -Po Huang","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University","ASUS Intelligent Cloud Services"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"ASUS Intelligent Cloud Services","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036438005","display_name":"Tzu-hsun Feng","orcid":"https://orcid.org/0009-0005-1993-6161"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Hsun Feng","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071751103","display_name":"Yu-Kuan Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Kuan Fu","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025040028","display_name":"Tsu-Yuan Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsu-Yuan Hsu","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056717057","display_name":"Po-Chieh Yen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Chieh Yen","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002538444","display_name":"Wei\u2010Cheng Tseng","orcid":"https://orcid.org/0000-0003-3528-8633"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Tseng","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073201681","display_name":"Kai\u2010Wei Chang","orcid":"https://orcid.org/0000-0002-4991-5274"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science","College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5112912495"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.7807,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92130574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.998199999332428,"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":0.7814281582832336},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7637183666229248},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6349958777427673},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6297908425331116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5778632164001465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5583265423774719},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4925268590450287},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44848713278770447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4370441138744354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3599327802658081},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3281008303165436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10264798998832703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814281582832336},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7637183666229248},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6349958777427673},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6297908425331116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5778632164001465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5583265423774719},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4925268590450287},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44848713278770447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4370441138744354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3599327802658081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3281008303165436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10264798998832703},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2219249508","https://openalex.org/W2289394825","https://openalex.org/W2508418541","https://openalex.org/W2593116425","https://openalex.org/W2972541922","https://openalex.org/W3036601975","https://openalex.org/W3174510164","https://openalex.org/W3203140070","https://openalex.org/W3205533980","https://openalex.org/W3209059054","https://openalex.org/W3209376089","https://openalex.org/W3209984917","https://openalex.org/W4224902884","https://openalex.org/W4225905067","https://openalex.org/W4226302796","https://openalex.org/W4232282348","https://openalex.org/W4281492411","https://openalex.org/W4296068785","https://openalex.org/W4297841520","https://openalex.org/W4297841557","https://openalex.org/W4297841583","https://openalex.org/W4319862442","https://openalex.org/W4319862641","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4387678054","https://openalex.org/W4306784355","https://openalex.org/W2784004155","https://openalex.org/W4246226292","https://openalex.org/W2150768546"],"abstract_inverted_index":{"Distilled":[0],"self-supervised":[1,23,37],"models":[2,39,61,83,92,107],"have":[3],"shown":[4],"competitive":[5],"performance":[6,103],"and":[7,44,53,62,120],"efficiency":[8],"in":[9,19,124],"recent":[10],"years.":[11],"However,":[12],"there":[13],"is":[14],"a":[15,76],"lack":[16],"of":[17,58,72,89,104,128],"experience":[18],"jointly":[20],"distilling":[21],"multiple":[22,77,90],"speech":[24,38,111],"models.":[25],"In":[26],"our":[27,99],"work,":[28],"we":[29,74],"performed":[30],"Ensemble":[31],"Knowledge":[32],"Distillation":[33],"(EKD)":[34],"on":[35,108],"various":[36],"such":[40],"as":[41],"HuBERT,":[42],"RobustHuBERT,":[43],"WavLM.":[45],"We":[46],"tried":[47],"two":[48],"different":[49,59,86],"aggregation":[50],"techniques,":[51],"layerwise-average":[52],"layerwise-concatenation,":[54],"to":[55,84],"the":[56,65,102,105,125,129],"representations":[57],"teacher":[60,91],"found":[63],"that":[64,98],"former":[66],"was":[67],"more":[68],"effective.":[69],"On":[70],"top":[71],"that,":[73],"proposed":[75],"prediction":[78],"head":[79],"method":[80,100],"for":[81],"student":[82],"predict":[85],"layer":[87],"outputs":[88],"simultaneously.":[93],"The":[94],"experimental":[95],"results":[96],"show":[97],"improves":[101],"distilled":[106],"four":[109],"downstream":[110],"processing":[112],"tasks,":[113],"Phoneme":[114],"Recognition,":[115,119],"Speaker":[116],"Identification,":[117],"Emotion":[118],"Automatic":[121],"Speech":[122],"Recognition":[123],"hidden-set":[126],"track":[127],"SUPERB":[130],"benchmark.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
