{"id":"https://openalex.org/W4375869164","doi":"https://doi.org/10.1109/icassp49357.2023.10094883","title":"An Adapter Based Multi-Label Pre-Training for Speech Separation and Enhancement","display_name":"An Adapter Based Multi-Label Pre-Training for Speech Separation and Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869164","doi":"https://doi.org/10.1109/icassp49357.2023.10094883"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094883","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/A5106558173","display_name":"Tianrui Wang","orcid":"https://orcid.org/0000-0002-2765-5889"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Shanghai,China","Peng Cheng Laboratory, Shenzhen, China","MoE Key Lab of Artificial Intelligence, AI Institute, 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,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,WA,USA","Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100295592","display_name":"Shu Yu","orcid":"https://orcid.org/0009-0004-9160-5343"},"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":"Shu Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Shanghai,China","MoE Key Lab of Artificial Intelligence, AI Institute, 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,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102492475","display_name":"Weibin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Zhu","raw_affiliation_strings":["Beijing Jiaotong University,Institute of Information Science,Beijing,China","Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Institute of Information Science,Beijing,China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6629,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84554909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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/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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9980999827384949,"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":0.7558776140213013},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.7391711473464966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6151135563850403},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6150587201118469},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.524665117263794},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4388744533061981},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4254996180534363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39462214708328247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3936738669872284},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3524143695831299},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24414753913879395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07073140144348145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558776140213013},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7391711473464966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6151135563850403},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6150587201118469},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.524665117263794},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4388744533061981},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4254996180534363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39462214708328247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3936738669872284},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3524143695831299},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24414753913879395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07073140144348145},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094883","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":[{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1606614440","https://openalex.org/W2005708641","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2896457183","https://openalex.org/W2964303773","https://openalex.org/W2970925270","https://openalex.org/W2972541922","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4221150474","https://openalex.org/W4224930323","https://openalex.org/W4225274946","https://openalex.org/W4225298533","https://openalex.org/W4226390724","https://openalex.org/W4226403810","https://openalex.org/W4285250921","https://openalex.org/W4297808394","https://openalex.org/W6636106077","https://openalex.org/W6718827390","https://openalex.org/W6759579507","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6803164887","https://openalex.org/W6810007534","https://openalex.org/W6810218461","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4306381730","https://openalex.org/W4229060448","https://openalex.org/W2981692913","https://openalex.org/W3184035966","https://openalex.org/W3044188621","https://openalex.org/W2160602540","https://openalex.org/W2485605994","https://openalex.org/W4385571108","https://openalex.org/W2146090693"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"self-supervised":[3],"learning":[4],"(SSL)":[5],"has":[6],"achieved":[7],"tremendous":[8],"success":[9],"in":[10,39,80],"various":[11],"speech":[12,31,40,68],"tasks":[13,28],"due":[14],"to":[15,18,129],"its":[16,104],"power":[17],"extract":[19],"representations":[20],"from":[21,36],"massive":[22],"unlabeled":[23],"data.":[24],"However,":[25],"compared":[26],"with":[27,166],"such":[29],"as":[30,140],"recognition":[32],"(ASR),":[33],"the":[34,56,74,98,130],"improvements":[35,159],"SSL":[37,57],"representation":[38],"separation":[41,75],"(SS)":[42],"and":[43,61,76,94,156,163],"enhancement":[44],"(SE)":[45],"are":[46,127],"considerably":[47],"smaller.":[48],"Based":[49],"on":[50,92,100,107,160],"HuBERT,":[51],"this":[52],"work":[53],"investigates":[54],"improving":[55],"model":[58],"for":[59,115],"SS":[60,93],"SE.":[62],"We":[63],"first":[64],"update":[65],"HuBERT\u2019s":[66,90,116],"masked":[67],"prediction":[69],"(MSP)":[70],"objective":[71],"by":[72],"integrating":[73],"denoising":[77],"terms,":[78],"resulting":[79],"a":[81,121,167],"multiple":[82,131,150],"pseudo":[83,132,151],"label":[84,133,152],"pre-training":[85],"scheme,":[86],"which":[87],"significantly":[88],"improves":[89],"performance":[91,99,105,158],"SE":[95],"but":[96],"degrades":[97],"ASR.":[101],"To":[102],"maintain":[103],"gain":[106],"ASR,":[108],"we":[109],"further":[110],"propose":[111],"an":[112],"adapter-based":[113,149],"architecture":[114],"Transformer":[117],"encoder,":[118],"where":[119],"only":[120,172],"few":[122],"parameters":[123,137,174],"of":[124],"each":[125],"layer":[126],"adjusted":[128],"MSP":[134],"while":[135],"other":[136],"remain":[138],"frozen":[139],"default":[141],"HuBERT.":[142],"Experimental":[143],"results":[144],"show":[145],"that":[146],"our":[147],"proposed":[148],"HuBERT":[153],"yield":[154],"consistent":[155],"significant":[157],"SE,":[161],"SS,":[162],"ASR":[164],"tasks,":[165],"faster":[168],"pretraining":[169],"speed,":[170],"at":[171],"marginal":[173],"increase.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}