{"id":"https://openalex.org/W4372271362","doi":"https://doi.org/10.1109/icassp49357.2023.10095596","title":"Self-Remixing: Unsupervised Speech Separation VIA Separation and Remixing","display_name":"Self-Remixing: Unsupervised Speech Separation VIA Separation and Remixing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372271362","doi":"https://doi.org/10.1109/icassp49357.2023.10095596"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095596","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/A5087117512","display_name":"Kohei Saijo","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087117512"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.4232,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81679915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"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":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":0.9990000128746033,"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":0.9933000206947327,"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/solver","display_name":"Solver","score":0.8049541711807251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7318969964981079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44398438930511475},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.4186096489429474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40469446778297424}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.8049541711807251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318969964981079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44398438930511475},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.4186096489429474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40469446778297424},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095596","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":[{"id":"https://metadata.un.org/sdg/10","score":0.4300000071525574,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W71081281","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W2125336414","https://openalex.org/W2141998673","https://openalex.org/W2460742184","https://openalex.org/W2763188033","https://openalex.org/W2899515918","https://openalex.org/W2905258586","https://openalex.org/W2908510526","https://openalex.org/W2933708090","https://openalex.org/W2963189033","https://openalex.org/W2982456909","https://openalex.org/W2998657200","https://openalex.org/W3016232124","https://openalex.org/W3016244615","https://openalex.org/W3093839391","https://openalex.org/W3097777922","https://openalex.org/W3163842642","https://openalex.org/W3168140565","https://openalex.org/W3197103473","https://openalex.org/W3202820684","https://openalex.org/W3205181379","https://openalex.org/W3206116612","https://openalex.org/W3207860153","https://openalex.org/W4221160586","https://openalex.org/W4224007376","https://openalex.org/W4292969786","https://openalex.org/W4296068764","https://openalex.org/W4296068789","https://openalex.org/W4296069145","https://openalex.org/W6629717138","https://openalex.org/W6633117090","https://openalex.org/W6638667902","https://openalex.org/W6678809451","https://openalex.org/W6718827390","https://openalex.org/W6744955691","https://openalex.org/W6749954789","https://openalex.org/W6756086276","https://openalex.org/W6757812555","https://openalex.org/W6757817989","https://openalex.org/W6760691258","https://openalex.org/W6762655374","https://openalex.org/W6769802879","https://openalex.org/W6770045915","https://openalex.org/W6773628751","https://openalex.org/W6777337586","https://openalex.org/W6784499681","https://openalex.org/W6802453432","https://openalex.org/W6809664633","https://openalex.org/W6810218788","https://openalex.org/W6810420261","https://openalex.org/W6840033097","https://openalex.org/W6843101493"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4213239787","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4377131110","https://openalex.org/W4388857216","https://openalex.org/W4294559962","https://openalex.org/W2046590706","https://openalex.org/W4390419005"],"abstract_inverted_index":{"We":[0],"present":[1],"Self-Remixing,":[2],"a":[3,11,22,26],"novel":[4],"self-supervised":[5,112],"speech":[6],"separation":[7,13,34],"method,":[8],"which":[9],"refines":[10],"pre-trained":[12],"model":[14],"in":[15,128,134],"an":[16],"unsupervised":[17,122],"manner.":[18],"Self-Remixing":[19,105,124],"consists":[20],"of":[21],"shuffler":[23,40],"module":[24],"and":[25,29,35,45,50,61],"solver":[27,56,72],"module,":[28],"they":[30],"grow":[31],"together":[32],"through":[33],"remixing":[36,51],"processes.":[37],"Specifically,":[38],"the":[39,52,59,63,68,76,82,89,93,96,115],"first":[41],"separates":[42,58],"observed":[43,69,77],"mixtures":[44,78],"makes":[46],"pseudo-mixtures":[47,60,97],"by":[48,87],"shuffling":[49],"separated":[53,64],"signals.":[54],"The":[55,71],"then":[57],"remixes":[62],"signals":[65],"back":[66],"to":[67],"mixtures.":[70],"is":[73],"trained":[74],"using":[75],"as":[79],"supervision,":[80],"while":[81],"shuffler\u2019s":[83],"weights":[84],"are":[85],"updated":[86],"taking":[88],"moving":[90],"average":[91],"with":[92,98,114],"solver\u2019s,":[94],"generating":[95],"fewer":[99],"distortions.":[100],"Our":[101],"experiments":[102],"demonstrate":[103],"that":[104],"gives":[106],"better":[107],"performance":[108],"over":[109],"existing":[110],"remixing-based":[111],"methods":[113],"same":[116],"or":[117],"less":[118],"training":[119],"costs":[120],"under":[121],"setup.":[123],"also":[125],"outperforms":[126],"baselines":[127],"semi-supervised":[129],"domain":[130],"adaptation,":[131],"showing":[132],"effectiveness":[133],"multiple":[135],"setups.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}