{"id":"https://openalex.org/W4221160587","doi":"https://doi.org/10.1109/jstsp.2022.3200911","title":"RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing","display_name":"RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4221160587","doi":"https://doi.org/10.1109/jstsp.2022.3200911"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3200911","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200911","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09864253.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09864253.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016864112","display_name":"Efthymios Tzinis","orcid":"https://orcid.org/0000-0002-1047-1338"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efthymios Tzinis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1047-1338","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Hebrew University of Jerusalem, Jerusalem, Israel"],"raw_orcid":"https://orcid.org/0000-0003-2237-3898","affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem, Jerusalem, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vamsi K. Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi K. Ithapu","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3027-7567","affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066528816","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-9621-9888"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0405,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7443935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"16","issue":"6","first_page":"1329","last_page":"1341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9232000112533569,"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":0.9232000112533569,"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":0.029999999329447746,"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/T11448","display_name":"Face recognition and analysis","score":0.014399999752640724,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.806713342666626},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6560019254684448},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6483713388442993},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.58170086145401},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5622029900550842},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5448323488235474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5341514348983765},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5314159989356995},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5289590358734131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5227246880531311},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4666445553302765},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4497973620891571},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4476116895675659},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.42049989104270935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3376990556716919},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17273065447807312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10901308059692383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806713342666626},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6560019254684448},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6483713388442993},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.58170086145401},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5622029900550842},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5448323488235474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5341514348983765},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5314159989356995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5289590358734131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5227246880531311},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666445553302765},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4497973620891571},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4476116895675659},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42049989104270935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3376990556716919},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17273065447807312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10901308059692383},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3200911","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200911","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09864253.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"doi:10.48550/arxiv.2202.08862","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2202.08862","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1109/jstsp.2022.3200911","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3200911","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09864253.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1957999595","display_name":null,"funder_award_id":"#2020-67021-32799","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G2926720356","display_name":null,"funder_award_id":"32799","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G5620962805","display_name":null,"funder_award_id":"67021","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G6770826516","display_name":null,"funder_award_id":"2020-67021-32799","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"}],"funders":[{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W2141998673","https://openalex.org/W2460742184","https://openalex.org/W2589857635","https://openalex.org/W2593116425","https://openalex.org/W2766672686","https://openalex.org/W2890820256","https://openalex.org/W2923728956","https://openalex.org/W2939518062","https://openalex.org/W2962843322","https://openalex.org/W2963189033","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2972864514","https://openalex.org/W2973220283","https://openalex.org/W2975955714","https://openalex.org/W2981436548","https://openalex.org/W2998616931","https://openalex.org/W2998678989","https://openalex.org/W3003875258","https://openalex.org/W3015219411","https://openalex.org/W3015337486","https://openalex.org/W3016912202","https://openalex.org/W3035160371","https://openalex.org/W3041561163","https://openalex.org/W3042857426","https://openalex.org/W3096338464","https://openalex.org/W3097034112","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3122264812","https://openalex.org/W3134695619","https://openalex.org/W3160085755","https://openalex.org/W3160320508","https://openalex.org/W3160733670","https://openalex.org/W3160799772","https://openalex.org/W3162538144","https://openalex.org/W3163114796","https://openalex.org/W3163652268","https://openalex.org/W3163816345","https://openalex.org/W3185109982","https://openalex.org/W3191469971","https://openalex.org/W3197103473","https://openalex.org/W3197227964","https://openalex.org/W3198098585","https://openalex.org/W4205689591","https://openalex.org/W4226029295","https://openalex.org/W4226219411","https://openalex.org/W6733814495","https://openalex.org/W6745136726","https://openalex.org/W6757632829","https://openalex.org/W6762114000","https://openalex.org/W6765939562","https://openalex.org/W6771787070","https://openalex.org/W6772349387","https://openalex.org/W6773005947","https://openalex.org/W6780218876","https://openalex.org/W6784499681","https://openalex.org/W6795747053","https://openalex.org/W6807926105"],"related_works":["https://openalex.org/W1226999","https://openalex.org/W10601565","https://openalex.org/W1970408","https://openalex.org/W589191","https://openalex.org/W14388539","https://openalex.org/W4883666","https://openalex.org/W1569375","https://openalex.org/W16400594","https://openalex.org/W9971014","https://openalex.org/W13477383"],"abstract_inverted_index":{"We":[0],"present":[1],"<italic":[2,57,93,157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3,58,94,158],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">RemixIT</i>":[4,59,159],",":[5],"a":[6,20,26,63,69,100],"simple":[7],"yet":[8],"effective":[9],"self-supervised":[10],"method":[11,149],"for":[12,80],"training":[13],"speech":[14,24,137],"enhancement":[15,138],"without":[16],"the":[17,86,114,118,125,129,145,189,197],"need":[18],"of":[19,33,103,128,147,192],"single":[21],"isolated":[22],"in-domain":[23,42,81],"nor":[25],"noise":[27,90],"waveform.":[28],"Our":[29,180],"approach":[30],"overcomes":[31],"limitations":[32],"previous":[34],"methods":[35],"which":[36,68,109],"make":[37],"them":[38,96],"dependent":[39],"on":[40,62,73,135,188],"clean":[41,88],"target":[43],"signals":[44,79,91],"and":[45,54,89,92,106,140,175],"thus,":[46],"sensitive":[47],"to":[48,112],"any":[49,164,173],"domain":[50,177],"mismatch":[51],"between":[52],"train":[53,113],"test":[55],"samples.":[56],"is":[60],"based":[61],"continuous":[64],"self-training":[65,194],"scheme":[66,195],"in":[67],"pre-trained":[70],"teacher":[71,119],"model":[72,166,199],"out-of-domain":[74],"data":[75],"infers":[76],"estimated":[77,87],"pseudo-target":[78],"mixtures.":[82],"Then,":[83],"by":[84],"permuting":[85],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">remixing</i>":[95],"together,":[97],"we":[98],"generate":[99],"new":[101],"set":[102],"bootstrapped":[104],"mixtures":[105],"corresponding":[107],"pseudo-targets":[108],"are":[110],"used":[111],"student":[115,131,198],"network.":[116],"Vice-versa,":[117],"periodically":[120],"refines":[121],"its":[122],"estimates":[123],"using":[124],"updated":[126],"parameters":[127],"latest":[130],"models.":[132],"Experimental":[133],"results":[134],"multiple":[136],"datasets":[139],"tasks":[141],"not":[142],"only":[143],"show":[144],"superiority":[146],"our":[148,193],"over":[150],"prior":[151],"approaches":[152],"but":[153],"also":[154],"showcase":[155],"that":[156],"can":[160],"be":[161,170],"combined":[162],"with":[163,183],"separation":[165],"as":[167,169],"well":[168],"applied":[171],"towards":[172],"semi-supervised":[174],"unsupervised":[176],"adaptation":[178],"task.":[179],"analysis,":[181],"paired":[182],"empirical":[184],"evidence,":[185],"sheds":[186],"light":[187],"inside":[190],"functioning":[191],"wherein":[196],"keeps":[200],"obtaining":[201],"better":[202],"performance":[203],"while":[204],"observing":[205],"severely":[206],"degraded":[207],"pseudo-targets.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-04-03T00:00:00"}