{"id":"https://openalex.org/W3160733670","doi":"https://doi.org/10.1109/icassp39728.2021.9413723","title":"Semi-Supervised Singing Voice Separation With Noisy Self-Training","display_name":"Semi-Supervised Singing Voice Separation With Noisy Self-Training","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160733670","doi":"https://doi.org/10.1109/icassp39728.2021.9413723","mag":"3160733670"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5102709539","display_name":"Zhepei Wang","orcid":"https://orcid.org/0000-0001-7845-5273"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhepei Wang","raw_affiliation_strings":["Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"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":"Ritwik Giri","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","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":"Umut Isik","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"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":"Jean-Marc Valin","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","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":"Arvindh Krishnaswamy","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102709539"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":2.7425,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90838404,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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":0.996999979019165,"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/singing","display_name":"Singing","score":0.8100171685218811},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7023710012435913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7000365853309631},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6531184911727905},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4906708002090454},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46794500946998596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44405829906463623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21792060136795044},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1880556046962738}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8100171685218811},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7023710012435913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000365853309631},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6531184911727905},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4906708002090454},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46794500946998596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44405829906463623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21792060136795044},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1880556046962738},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2062710265","https://openalex.org/W2124539664","https://openalex.org/W2669032454","https://openalex.org/W2903718461","https://openalex.org/W2916985722","https://openalex.org/W2938709889","https://openalex.org/W2963452667","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2964229681","https://openalex.org/W2971458685","https://openalex.org/W2972411915","https://openalex.org/W2981892560","https://openalex.org/W2985214749","https://openalex.org/W2990594533","https://openalex.org/W3009355670","https://openalex.org/W3012897083","https://openalex.org/W3015753416","https://openalex.org/W3026041220","https://openalex.org/W3035160371","https://openalex.org/W3035268204","https://openalex.org/W3036605642","https://openalex.org/W3037149862","https://openalex.org/W3040688604","https://openalex.org/W3097034112","https://openalex.org/W3104704316","https://openalex.org/W3113680622","https://openalex.org/W3113792747","https://openalex.org/W4298310324","https://openalex.org/W4393895285","https://openalex.org/W6751512325","https://openalex.org/W6766320909","https://openalex.org/W6769478989","https://openalex.org/W6770592442","https://openalex.org/W6774995033","https://openalex.org/W6775000844","https://openalex.org/W6775369996","https://openalex.org/W6780053291","https://openalex.org/W6781755050","https://openalex.org/W6785597316","https://openalex.org/W6863176869"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2],"singing":[3],"voice":[4],"separation":[5],"has":[6,24],"primarily":[7],"focused":[8],"on":[9,65,87],"supervised":[10,118],"deep":[11],"learning":[12],"methods.":[13,119],"However,":[14],"the":[15,51,55,66,74,97,108],"scarcity":[16],"of":[17,34,46,77],"ground-truth":[18,89],"data":[19,48,103],"with":[20,102],"clean":[21],"musical":[22],"sources":[23],"been":[25],"a":[26,31,39,43,62,81],"problem":[27],"for":[28],"long.":[29],"Given":[30],"limited":[32],"set":[33],"labeled":[35,68],"data,":[36],"we":[37,59],"present":[38],"method":[40],"to":[41,49,117],"leverage":[42,107],"large":[44,75,109],"volume":[45],"unlabeled":[47,78,110],"improve":[50],"model\u2019s":[52],"performance.":[53],"Following":[54],"noisy":[56],"self-training":[57,99],"framework,":[58],"first":[60],"train":[61],"teacher":[63],"network":[64,84],"small":[67],"dataset":[69],"and":[70,90,112],"infer":[71],"pseudo-labels":[72],"from":[73],"corpus":[76,111],"mixtures.":[79],"Then,":[80],"larger":[82],"student":[83],"is":[85],"trained":[86],"combined":[88],"self-labeled":[91],"datasets.":[92],"Empirical":[93],"results":[94],"show":[95],"that":[96],"proposed":[98],"scheme,":[100],"along":[101],"augmentation":[104],"methods,":[105],"effectively":[106],"obtain":[113],"superior":[114],"performance":[115],"compared":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}