{"id":"https://openalex.org/W4221160586","doi":"https://doi.org/10.1109/icassp43922.2022.9746655","title":"Remix-Cycle-Consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation","display_name":"Remix-Cycle-Consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221160586","doi":"https://doi.org/10.1109/icassp43922.2022.9746655"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746655","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":"conference-paper","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/A5013385059","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":false,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.9228,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72919818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4373","last_page":"4377"},"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6631374359130859},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5380181074142456},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4855053424835205},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4543139934539795},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4542451798915863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4471818506717682},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.41532281041145325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36303603649139404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3136022686958313},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2824940085411072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6631374359130859},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5380181074142456},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4855053424835205},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4543139934539795},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4542451798915863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4471818506717682},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.41532281041145325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36303603649139404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3136022686958313},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2824940085411072}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746655","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2042860487","https://openalex.org/W2066218102","https://openalex.org/W2141998673","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2558649592","https://openalex.org/W2600556233","https://openalex.org/W2763188033","https://openalex.org/W2787069756","https://openalex.org/W2802304149","https://openalex.org/W2888858245","https://openalex.org/W2905258586","https://openalex.org/W2949558265","https://openalex.org/W2954695182","https://openalex.org/W2963341071","https://openalex.org/W2998832642","https://openalex.org/W3012110132","https://openalex.org/W3031135612","https://openalex.org/W3034771406","https://openalex.org/W3095166612","https://openalex.org/W3096159803","https://openalex.org/W3102190437","https://openalex.org/W3197324213","https://openalex.org/W4320013936","https://openalex.org/W6735168207","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W2949601986","https://openalex.org/W2067569035","https://openalex.org/W2090985514","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458"],"abstract_inverted_index":{"A":[0],"new":[1],"learning":[2,56,156],"algorithm":[3],"for":[4,41],"speech":[5,95,102,144],"separation":[6,35,82,138,145,153],"networks":[7,27,36],"is":[8,45,87],"designed":[9],"to":[10,30,77,126,159],"explicitly":[11],"reduce":[12],"residual":[13],"noise":[14],"and":[15,58,74,99,113,155],"artifacts":[16],"in":[17,21,33,130,133],"the":[18,38,42,55,65,90,93,100,106,110,131,134,137,148],"separated":[19],"signal":[20,44],"an":[22,127],"unsupervised":[23],"manner.":[24],"Generative":[25],"adversarial":[26],"are":[28],"known":[29],"be":[31],"effective":[32],"constructing":[34],"when":[37],"ground":[39],"truth":[40],"observed":[43,96],"inaccessible.":[46],"Still,":[47],"weak":[48],"objectives":[49],"aimed":[50],"at":[51,97],"distribution-to-distribution":[52],"mapping":[53],"make":[54],"unstable":[57],"limit":[59],"their":[60],"performance.":[61],"This":[62],"study":[63],"introduces":[64],"remix-cycle-consistency":[66,85],"loss":[67,86,124],"as":[68,89],"a":[69],"more":[70],"appropriate":[71],"objective":[72],"function":[73],"uses":[75],"it":[76],"fine-tune":[78],"adversarially":[79],"learned":[80],"source":[81],"models.":[83],"The":[84,120],"de-fined":[88],"difference":[91],"between":[92],"mixed":[94,111],"microphones":[98],"pseudo-mixed":[101],"obtained":[103],"by":[104],"alternating":[105],"process":[107],"of":[108,122,136],"separating":[109],"sound":[112],"remixing":[114],"its":[115],"outputs":[116],"with":[117,142],"another":[118],"combination.":[119],"minimization":[121],"this":[123],"leads":[125],"explicit":[128],"reduction":[129],"distortions":[132],"output":[135],"network.":[139],"Experimental":[140],"comparisons":[141],"multichannel":[143],"demonstrated":[146],"that":[147],"proposed":[149],"method":[150],"achieved":[151],"high":[152],"accuracy":[154],"stability":[157],"comparable":[158],"supervised":[160],"learning.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}