{"id":"https://openalex.org/W4391021774","doi":"https://doi.org/10.1109/asru57964.2023.10389685","title":"FAT-HuBERT: Front-End Adaptive Training of Hidden-Unit BERT For Distortion-Invariant Robust Speech Recognition","display_name":"FAT-HuBERT: Front-End Adaptive Training of Hidden-Unit BERT For Distortion-Invariant Robust Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021774","doi":"https://doi.org/10.1109/asru57964.2023.10389685"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5085570577","display_name":"Dongning Yang","orcid":"https://orcid.org/0009-0003-6832-7122"},"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":"Dongning Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, 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 Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392341","display_name":"Wei Wang","orcid":"https://orcid.org/0009-0008-3706-483X"},"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 Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, 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 Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, 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 Department of Computer Science and Engineering,Shanghai,China","AI Institute Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, 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 Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, 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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9998999834060669,"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":0.9908999800682068,"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":0.7252972722053528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.723873496055603},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6906342506408691},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5978720188140869},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5799506306648254},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.4911911189556122},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45545074343681335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3782771825790405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3388060927391052},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3192281126976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252972722053528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.723873496055603},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6906342506408691},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5978720188140869},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5799506306648254},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.4911911189556122},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45545074343681335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3782771825790405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3388060927391052},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3192281126976013},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989034586","https://openalex.org/W2024490156","https://openalex.org/W2296167893","https://openalex.org/W2559260703","https://openalex.org/W2618099328","https://openalex.org/W2755891984","https://openalex.org/W2842511635","https://openalex.org/W2933138175","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2972320711","https://openalex.org/W2972436155","https://openalex.org/W2972541922","https://openalex.org/W3008912312","https://openalex.org/W3015199127","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3036601975","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3109196171","https://openalex.org/W3135915893","https://openalex.org/W3197411683","https://openalex.org/W3205533980","https://openalex.org/W3206531472","https://openalex.org/W3209059054","https://openalex.org/W3209376089","https://openalex.org/W3209984917","https://openalex.org/W4224919704","https://openalex.org/W4224938485","https://openalex.org/W4281807971","https://openalex.org/W4297808394","https://openalex.org/W4297841603","https://openalex.org/W4306672449","https://openalex.org/W4310630515","https://openalex.org/W4372260292","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757632829","https://openalex.org/W6780218876","https://openalex.org/W6809874571","https://openalex.org/W6839558599","https://openalex.org/W6846365670","https://openalex.org/W6846849147","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2401089611","https://openalex.org/W1883089835"],"abstract_inverted_index":{"Advancements":[0],"in":[1,136],"monaural":[2],"speech":[3,21,113,122],"enhancement":[4],"(SE)":[5],"techniques":[6,18],"have":[7],"greatly":[8],"improved":[9],"the":[10,28,35,40,61,67,71,93,106,124],"perceptual":[11],"quality":[12],"of":[13,37,63,102,108],"speech.":[14],"However,":[15],"integrating":[16],"these":[17],"into":[19],"automatic":[20],"recognition":[22],"(ASR)":[23],"systems":[24],"has":[25],"not":[26],"yielded":[27],"expected":[29],"performance":[30,107],"gains,":[31],"primarily":[32],"due":[33],"to":[34,59],"introduction":[36],"distortions":[38,68],"during":[39],"SE":[41,72,94],"process.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,74],"propose":[47],"a":[48,100,132],"novel":[49],"approach":[50],"called":[51],"FAT-HuBERT,":[52],"which":[53],"leverages":[54],"distortion-invariant":[55],"self-supervised":[56],"learning":[57],"(SSL)":[58],"enhance":[60],"robustness":[62],"ASR.":[64],"To":[65],"address":[66],"introduced":[69],"by":[70],"frontends,":[73],"introduce":[75],"layer-wise":[76],"fusion":[77],"modules":[78],"that":[79],"incorporate":[80],"features":[81],"extracted":[82],"from":[83,99,115,123],"both":[84],"observed":[85],"noisy":[86,112,121],"signals":[87],"and":[88],"enhanced":[89],"signals.":[90],"During":[91],"training,":[92],"frontend":[95],"is":[96],"randomly":[97],"selected":[98],"pool":[101],"models.":[103],"We":[104],"evaluate":[105],"FAT-HuBERT":[109],"on":[110],"simulated":[111],"generated":[114],"LIBRISPEECH":[116],"as":[117,119],"well":[118],"real-world":[120],"CHIME-4":[125],"1-channel":[126],"dataset.":[127],"The":[128],"experimental":[129],"results":[130],"demonstrate":[131],"significant":[133],"relative":[134],"reduction":[135],"word":[137],"error":[138],"rate":[139],"(WER).":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}