{"id":"https://openalex.org/W4392909819","doi":"https://doi.org/10.1109/icassp48485.2024.10447573","title":"Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement","display_name":"Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909819","doi":"https://doi.org/10.1109/icassp48485.2024.10447573"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5028862537","display_name":"Ching-Hua Lee","orcid":"https://orcid.org/0000-0001-6116-3653"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ching-Hua Lee","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071383028","display_name":"Chouchang Yang","orcid":"https://orcid.org/0009-0007-3506-6121"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chouchang Yang","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039893379","display_name":"Rakshith Sharma Srinivasa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakshith Sharma Srinivasa","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040083798","display_name":"Yashas Malur Saidutta","orcid":"https://orcid.org/0000-0002-8487-0219"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashas Malur Saidutta","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059500729","display_name":"Jaejin Cho","orcid":"https://orcid.org/0000-0001-5672-6765"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaejin Cho","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058974318","display_name":"Yilin Shen","orcid":"https://orcid.org/0000-0002-1955-1529"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilin Shen","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044205212","display_name":"Hongxia Jin","orcid":"https://orcid.org/0009-0000-0222-4217"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongxia Jin","raw_affiliation_strings":["Samsung Research,America","Samsung Research, America"],"affiliations":[{"raw_affiliation_string":"Samsung Research,America","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Samsung Research, America","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028862537"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":1.9754,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86147324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10831","last_page":"10835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9879000186920166,"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":0.9879000186920166,"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":0.9624999761581421,"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/computer-science","display_name":"Computer science","score":0.7792111039161682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6995625495910645},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6110998392105103},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6081118583679199},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.502929151058197},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4620024859905243},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43871617317199707},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4375155568122864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39528781175613403},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3273543119430542},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07174485921859741},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06072536110877991},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0601373016834259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792111039161682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6995625495910645},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6110998392105103},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6081118583679199},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.502929151058197},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4620024859905243},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43871617317199707},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4375155568122864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39528781175613403},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3273543119430542},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07174485921859741},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06072536110877991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0601373016834259},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2052623686","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2153894152","https://openalex.org/W2187089797","https://openalex.org/W2559809918","https://openalex.org/W2603567530","https://openalex.org/W2962866211","https://openalex.org/W2962997440","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2971417062","https://openalex.org/W2973049979","https://openalex.org/W2973220283","https://openalex.org/W3003986888","https://openalex.org/W3011500442","https://openalex.org/W3015893539","https://openalex.org/W3016129867","https://openalex.org/W3096217733","https://openalex.org/W3096408984","https://openalex.org/W3113290170","https://openalex.org/W3162188526","https://openalex.org/W3191448984","https://openalex.org/W3197284240","https://openalex.org/W3197580070","https://openalex.org/W3206558844","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210484003","https://openalex.org/W4224933800","https://openalex.org/W4226403810","https://openalex.org/W4232282348","https://openalex.org/W4367190594","https://openalex.org/W4372266927","https://openalex.org/W4375869372","https://openalex.org/W4385823298","https://openalex.org/W6639480849","https://openalex.org/W6773536332","https://openalex.org/W6780218876","https://openalex.org/W6803559545","https://openalex.org/W6851660269"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W3160071434"],"abstract_inverted_index":{"Deep":[0],"learning":[1,135],"based":[2,137],"speech":[3,138,149],"enhancement":[4],"(SE)":[5],"approaches":[6],"could":[7],"suffer":[8],"from":[9,33,98,108],"performance":[10,65],"degradation":[11],"due":[12],"to":[13,41,80,151,172,183],"mismatch":[14],"between":[15],"training":[16],"and":[17,157],"testing":[18],"environments.":[19],"A":[20],"realistic":[21],"situation":[22],"is":[23,77,84,179],"that":[24,71,93],"an":[25],"SE":[26,92,116,131,170],"model":[27],"trained":[28],"on":[29],"parallel":[30],"noisy-clean":[31],"utterances":[32],"one":[34],"environment,":[35,46],"the":[36,47,62,99,105,109,118,162,180],"source":[37,110],"domain,":[38,72,101],"may":[39],"fail":[40],"perform":[42],"adequately":[43],"in":[44,70,73,117,155,190],"another":[45],"target":[48,63,100],"(new)":[49],"domain":[50,64,88,111,188],"of":[51,147,164],"unseen":[52],"acoustic":[53],"or":[54],"noise":[55],"conditions.":[56],"Even":[57],"though":[58],"we":[59,124],"can":[60],"improve":[61],"by":[66,132],"leveraging":[67,133,165],"paired":[68,112],"data":[69,76,97,150],"reality,":[74],"noisy":[75,96],"more":[78],"straightforward":[79],"collect.":[81],"Therefore,":[82],"it":[83,178],"worth":[85],"studying":[86],"unsupervised":[87],"adaptation":[89,128,171,189],"techniques":[90],"for":[91,114,130,168,187],"utilize":[94],"only":[95],"together":[102],"with":[103,144],"exploiting":[104],"knowledge":[106],"available":[107],"data,":[113],"improved":[115],"new":[119,173],"domain.":[120],"In":[121],"this":[122],"paper,":[123],"present":[125],"a":[126],"novel":[127],"framework":[129],"self-supervised":[134],"(SSL)":[136],"models.":[139],"SSL":[140,166,185],"models":[141,186],"are":[142],"pre-trained":[143],"large":[145],"amount":[146],"raw":[148],"extract":[152],"representations":[153,167],"rich":[154],"phonetic":[156],"acoustics":[158],"information.":[159],"We":[160],"explore":[161],"potential":[163],"effective":[169],"domains.":[174],"To":[175],"our":[176],"knowledge,":[177],"first":[181],"attempt":[182],"apply":[184],"SE.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}