{"id":"https://openalex.org/W4372260292","doi":"https://doi.org/10.1109/icassp49357.2023.10096308","title":"HuBERT-AGG: Aggregated Representation Distillation of Hidden-Unit Bert for Robust Speech Recognition","display_name":"HuBERT-AGG: Aggregated Representation Distillation of Hidden-Unit Bert for Robust Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260292","doi":"https://doi.org/10.1109/icassp49357.2023.10096308"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096308","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":"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/A5100391659","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-5367-7056"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929797768592834},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7644995450973511},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7200850248336792},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6107690930366516},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49672967195510864},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4919690787792206},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47594428062438965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46509993076324463},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43928971886634827},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.41203033924102783},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2740401327610016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929797768592834},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7644995450973511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7200850248336792},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6107690930366516},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49672967195510864},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4919690787792206},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47594428062438965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46509993076324463},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43928971886634827},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41203033924102783},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2740401327610016},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096308","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":"Peace, Justice and strong institutions","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989034586","https://openalex.org/W2024490156","https://openalex.org/W2078528584","https://openalex.org/W2219249508","https://openalex.org/W2559260703","https://openalex.org/W2885724687","https://openalex.org/W2889442120","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2963341071","https://openalex.org/W2980451698","https://openalex.org/W2995181338","https://openalex.org/W2998161426","https://openalex.org/W2998616931","https://openalex.org/W3005680577","https://openalex.org/W3008912312","https://openalex.org/W3015213852","https://openalex.org/W3032514799","https://openalex.org/W3036601975","https://openalex.org/W3096408984","https://openalex.org/W3139918052","https://openalex.org/W3197411683","https://openalex.org/W3197580070","https://openalex.org/W3198270883","https://openalex.org/W3198608154","https://openalex.org/W3205533980","https://openalex.org/W3209059054","https://openalex.org/W3209376089","https://openalex.org/W4221138681","https://openalex.org/W4224919704","https://openalex.org/W4226033575","https://openalex.org/W4226390724","https://openalex.org/W4297841603","https://openalex.org/W4385245566","https://openalex.org/W6656414902","https://openalex.org/W6688816777","https://openalex.org/W6735429107","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6780218876","https://openalex.org/W6791904447","https://openalex.org/W6809874571"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2121652828","https://openalex.org/W151018310","https://openalex.org/W3081187864"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3],"attracted":[4],"widespread":[5],"research":[6],"interest":[7],"since":[8],"many":[9],"successful":[10],"SSL":[11,46,60,182],"approaches":[12,183],"such":[13,28],"as":[14,29,131,178,180,189],"wav2vec":[15],"2.0":[16],"and":[17,117],"Hidden-unit":[18],"BERT":[19],"(HuBERT)":[20],"have":[21,37,165],"achieved":[22,170],"promising":[23],"results":[24,169],"on":[25,93,106,134,152],"speech-related":[26],"tasks":[27],"automatic":[30],"speech":[31,64,110,130,161],"recognition":[32,65],"(ASR).":[33],"However,":[34],"few":[35],"works":[36],"been":[38],"conducted":[39],"to":[40],"improve":[41],"the":[42,78,107,114,153,167,185],"noise":[43],"robustness":[44],"of":[45,81,85,97],"models.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,72,164],"propose":[52],"HuBERT-AGG,":[53],"a":[54,86,94,101,123],"novel":[55],"method":[56],"that":[57,76],"learns":[58],"noise-invariant":[59],"representations":[61,116],"for":[62],"robust":[63],"by":[66,90,111,122,171],"distilling":[67,112],"aggregated":[68,115],"layer-wise":[69,118],"representations.":[70],"Specifically,":[71],"learn":[73],"an":[74],"aggregator":[75],"computes":[77],"weighted":[79],"sum":[80],"all":[82,172],"hidden":[83,119],"states":[84,120],"pretrained":[87,124],"vanilla":[88,125],"Hu-BERT":[89],"fine-tuning":[91],"it":[92],"small":[95],"portion":[96],"labeled":[98],"data.":[99],"Then":[100],"noise-robust":[102],"HuBERT":[103,126],"is":[104],"trained":[105],"simulated":[108,136],"noisy":[109,137],"from":[113],"produced":[121],"with":[127,148],"parallel":[128],"original":[129,154],"input.":[132],"Experiments":[133],"libriSpeech":[135],"test":[138,155,162],"sets":[139],"show":[140],"13.1%-17.0%":[141],"relative":[142],"word":[143],"error":[144],"rate":[145],"(WER)":[146],"reduction":[147],"very":[149],"slight":[150],"degradation":[151],"sets.":[156],"On":[157],"CHiME-4":[158],"1-channel":[159],"real":[160],"sets,":[163],"surpassed":[166],"best":[168],"published":[173],"fully":[174],"supervised":[175],"ASR":[176],"models":[177],"well":[179],"other":[181],"adopting":[184],"same":[186],"data":[187],"usage":[188],"ours.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}