{"id":"https://openalex.org/W4408356835","doi":"https://doi.org/10.1109/icassp49660.2025.10888360","title":"Leveraging Out-of-Domain Noise for Unsupervised Domain Adaptation in Speech Enhancement","display_name":"Leveraging Out-of-Domain Noise for Unsupervised Domain Adaptation in Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356835","doi":"https://doi.org/10.1109/icassp49660.2025.10888360"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5032906456","display_name":"Yu Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Liao","raw_affiliation_strings":["Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035701962","display_name":"Haixin Guan","orcid":"https://orcid.org/0000-0001-8880-449X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haixin Guan","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917656","display_name":"Shuang Wei","orcid":"https://orcid.org/0000-0002-6250-6926"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Wei","raw_affiliation_strings":["Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,China","institution_ids":["https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032906456"],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":null,"apc_paid":null,"fwci":2.5565,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87438575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"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/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"}},"topics":[{"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9520000219345093,"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":0.707373857498169},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6850194931030273},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.65155428647995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.607320249080658},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.579522430896759},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.537656843662262},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4889789819717407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3032417297363281},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22970694303512573},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10098573565483093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08651390671730042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707373857498169},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6850194931030273},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.65155428647995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.607320249080658},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.579522430896759},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.537656843662262},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4889789819717407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3032417297363281},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22970694303512573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10098573565483093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08651390671730042},{"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/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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2141998673","https://openalex.org/W2510942155","https://openalex.org/W2603567530","https://openalex.org/W2964058413","https://openalex.org/W2973220283","https://openalex.org/W3011500442","https://openalex.org/W3092609815","https://openalex.org/W3122264812","https://openalex.org/W3147966746","https://openalex.org/W3197227964","https://openalex.org/W3205181379","https://openalex.org/W3206558844","https://openalex.org/W3207551191","https://openalex.org/W4225302959","https://openalex.org/W4232282348","https://openalex.org/W4292969786","https://openalex.org/W4383961998","https://openalex.org/W4385822305","https://openalex.org/W4385822654","https://openalex.org/W4385823085","https://openalex.org/W4388620484","https://openalex.org/W4389315133","https://openalex.org/W4389607163","https://openalex.org/W4390604176","https://openalex.org/W4391164125","https://openalex.org/W4392903364","https://openalex.org/W4392903924","https://openalex.org/W4392903938","https://openalex.org/W4392909819","https://openalex.org/W4402111353","https://openalex.org/W4402112285","https://openalex.org/W4406461266","https://openalex.org/W4410314146","https://openalex.org/W6749271710"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W3203792196","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W2955455867"],"abstract_inverted_index":{"When":[0],"there\u2019s":[1],"a":[2,44,69,90],"mismatch":[3],"between":[4],"the":[5,27,64,76,97,108,126,156],"training":[6,33,81,94],"and":[7,34,132,165],"test":[8,167],"domains,":[9],"supervised":[10],"speech":[11,147],"enhancement":[12,148],"(SE)":[13],"models":[14],"trained":[15],"on":[16,140,162],"synthetic":[17],"paired":[18,70,104],"noisy-clean":[19],"data":[20,82,127],"often":[21],"struggle":[22],"in":[23,58],"real-world":[24],"scenarios,":[25],"highlighting":[26],"industry\u2019s":[28],"strong":[29],"demand":[30],"for":[31,47,145],"unsupervised":[32,55,71,142],"domain":[35,56,80,143],"adaptation":[36,57,144],"methods.":[37],"In":[38],"this":[39],"study,":[40],"we":[41],"introduce":[42],"PHA-ReMixIT,":[43],"novel":[45],"approach":[46],"leveraging":[48],"out-of-domain":[49],"(OOD)":[50],"noise":[51,85,92],"signals":[52],"to":[53,95,110,123],"enhance":[54],"SE.":[59],"Our":[60],"method":[61],"builds":[62],"upon":[63],"state-of-the-art":[65],"ReMixIT":[66,157],"by":[67],"introducing":[68],"remixing":[72],"technique,":[73],"which":[74],"augments":[75],"diversity":[77],"of":[78,129],"target":[79],"with":[83,102],"OOD":[84,98,133],"signals.":[86],"We":[87],"further":[88],"propose":[89],"heterogeneous":[91,105],"invariant":[93],"align":[96],"augmented":[99],"noisy":[100,134],"mixtures":[101,135],"their":[103],"counterparts,":[106],"encouraging":[107],"model":[109,137],"output":[111],"cleaner":[112],"speech.":[113],"Additionally,":[114],"an":[115],"adaptive":[116],"focal":[117],"weighting":[118],"mechanism":[119],"is":[120],"also":[121],"introduced":[122],"dynamically":[124],"emphasize":[125],"importance":[128],"both":[130,163],"in-domain":[131],"during":[136],"adaptation.":[138],"Experiments":[139],"CHiME-7":[141],"conversational":[146],"(UDASE)":[149],"task":[150],"demonstrate":[151],"that":[152],"PHA-ReMixIT":[153],"significantly":[154],"outperforms":[155],"baseline,":[158],"boosting":[159],"SE":[160],"performance":[161],"real":[164],"synthesized":[166],"sets.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}