{"id":"https://openalex.org/W3205181379","doi":"https://doi.org/10.1109/icassp43922.2022.9747463","title":"Continual Self-Training With Bootstrapped Remixing For Speech Enhancement","display_name":"Continual Self-Training With Bootstrapped Remixing For Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205181379","doi":"https://doi.org/10.1109/icassp43922.2022.9747463","mag":"3205181379"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747463","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.10103","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Meta AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna 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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.452,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83852691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6947","last_page":"6951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.6691655516624451},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6271853446960449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5714420080184937},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48725929856300354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3062419295310974},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07326534390449524},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05754479765892029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6691655516624451},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6271853446960449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5714420080184937},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48725929856300354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3062419295310974},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07326534390449524},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05754479765892029},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747463","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.10103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.10103","pdf_url":"https://arxiv.org/pdf/2110.10103","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.10103","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.10103","pdf_url":"https://arxiv.org/pdf/2110.10103","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1983108229","https://openalex.org/W2141998673","https://openalex.org/W2939518062","https://openalex.org/W2963189033","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2998572311","https://openalex.org/W2998678989","https://openalex.org/W3042857426","https://openalex.org/W3090388844","https://openalex.org/W3093839391","https://openalex.org/W3094607766","https://openalex.org/W3096338464","https://openalex.org/W3097034112","https://openalex.org/W3097906045","https://openalex.org/W3100954996","https://openalex.org/W3122264812","https://openalex.org/W3134695619","https://openalex.org/W3160085755","https://openalex.org/W3160733670","https://openalex.org/W3162538144","https://openalex.org/W3163114796","https://openalex.org/W3163816345","https://openalex.org/W3164223074","https://openalex.org/W3167575587","https://openalex.org/W3169165652","https://openalex.org/W3191469971","https://openalex.org/W3197103473","https://openalex.org/W3197223534","https://openalex.org/W3197227964","https://openalex.org/W3198098585","https://openalex.org/W3200639435","https://openalex.org/W4205689591","https://openalex.org/W4226219411","https://openalex.org/W4232282348","https://openalex.org/W6631190155","https://openalex.org/W6633117090","https://openalex.org/W6772349387","https://openalex.org/W6783462664","https://openalex.org/W6784499681","https://openalex.org/W6791446376","https://openalex.org/W6795747053"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"We":[0],"propose":[1],"RemixIT,":[2],"a":[3,19,44,63,128],"simple":[4],"and":[5,36,54,82,133,152],"novel":[6],"self-supervised":[7,118],"training":[8],"method":[9,15],"for":[10,31,62,131,137],"speech":[11,122,138],"enhancement.":[12],"The":[13],"proposed":[14],"is":[16,48,55,89],"based":[17],"on":[18,50],"continuously":[20],"self-training":[21],"scheme":[22],"that":[23,112],"overcomes":[24],"limitations":[25],"from":[26],"previous":[27,116],"studies":[28],"including":[29],"assumptions":[30],"the":[32,71,86,92,105],"in-domain":[33,66],"noise":[34,83],"distribution":[35],"having":[37],"access":[38],"to":[39,57,145,148],"clean":[40,81],"target":[41,60],"signals.":[42,84],"Specifically,":[43],"separation":[45,150,156],"teacher":[46],"model":[47,88],"pre-trained":[49],"an":[51],"out-of-domain":[52],"dataset":[53],"used":[56],"infer":[58],"estimated":[59,80,94],"signals":[61],"batch":[64],"of":[65],"mixtures.":[67],"Next,":[68],"we":[69,99],"bootstrap":[70],"mixing":[72],"process":[73],"by":[74],"generating":[75],"artificial":[76],"mixtures":[77],"using":[78,91,104],"permuted":[79,93],"Finally,":[85],"student":[87,107],"trained":[90],"sources":[95],"as":[96],"targets":[97],"while":[98,141],"periodically":[100],"update":[101],"teacher\u2019s":[102],"weights":[103],"latest":[106],"model.":[108,157],"Our":[109],"experiments":[110],"show":[111],"RemixIT":[113,126],"outperforms":[114],"several":[115],"state-of-the-art":[117],"methods":[119],"under":[120],"multiple":[121],"enhancement":[123,139],"tasks.":[124],"Additionally,":[125],"provides":[127],"seamless":[129],"alternative":[130],"semi-supervised":[132],"unsupervised":[134],"domain":[135],"adaptation":[136],"tasks,":[140],"being":[142],"general":[143],"enough":[144],"be":[146],"applied":[147],"any":[149,155],"task":[151],"paired":[153],"with":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}