{"id":"https://openalex.org/W3161042404","doi":"https://doi.org/10.1109/icassp39728.2021.9414398","title":"Complex Ratio Masking For Singing Voice Separation","display_name":"Complex Ratio Masking For Singing Voice Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161042404","doi":"https://doi.org/10.1109/icassp39728.2021.9414398","mag":"3161042404"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414398","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/A5100396613","display_name":"Yixuan Zhang","orcid":"https://orcid.org/0000-0002-1924-9848"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yixuan Zhang","raw_affiliation_strings":["The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800003","display_name":"Yuzhou Liu","orcid":"https://orcid.org/0000-0002-7030-9121"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhou Liu","raw_affiliation_strings":["The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA","The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100396613"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78526031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"45"},"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":0.9998000264167786,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.8275253772735596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7495611906051636},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6964904069900513},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6540139317512512},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6417865753173828},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6272401809692383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6268619298934937},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.448230504989624},{"id":"https://openalex.org/keywords/auditory-masking","display_name":"Auditory masking","score":0.41606104373931885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.362691193819046},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.30294865369796753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11824959516525269},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.11737436056137085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08513537049293518}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.8275253772735596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495611906051636},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6964904069900513},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6540139317512512},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6417865753173828},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6272401809692383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6268619298934937},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.448230504989624},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.41606104373931885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.362691193819046},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.30294865369796753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11824959516525269},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.11737436056137085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08513537049293518},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414398","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1964208564","https://openalex.org/W2048142341","https://openalex.org/W2113990625","https://openalex.org/W2157266364","https://openalex.org/W2291877678","https://openalex.org/W2296724634","https://openalex.org/W2304609584","https://openalex.org/W2407685581","https://openalex.org/W2563534197","https://openalex.org/W2594251744","https://openalex.org/W2669032454","https://openalex.org/W2796571515","https://openalex.org/W2806304431","https://openalex.org/W2889134433","https://openalex.org/W2916985722","https://openalex.org/W2962866211","https://openalex.org/W2963452667","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2964121744","https://openalex.org/W2964229681","https://openalex.org/W2969230224","https://openalex.org/W2972460025","https://openalex.org/W2972653970","https://openalex.org/W2990594533","https://openalex.org/W2991361823","https://openalex.org/W3012897083","https://openalex.org/W4285719527","https://openalex.org/W6631190155","https://openalex.org/W6697040288","https://openalex.org/W6714030504","https://openalex.org/W6745457739","https://openalex.org/W6751512325","https://openalex.org/W6775369996"],"related_works":["https://openalex.org/W2140659649","https://openalex.org/W2010677552","https://openalex.org/W2218947444","https://openalex.org/W2411742137","https://openalex.org/W2109316093","https://openalex.org/W1602745308","https://openalex.org/W2990940109","https://openalex.org/W4205619918","https://openalex.org/W1988918813","https://openalex.org/W2055429703"],"abstract_inverted_index":{"Music":[0],"source":[1],"separation":[2,41,86],"is":[3,81],"important":[4],"for":[5,31,51,73,99],"applications":[6],"such":[7],"as":[8],"karaoke":[9],"and":[10,24,53,68,103],"remixing.":[11],"Much":[12],"of":[13,71],"previous":[14],"research":[15],"focuses":[16],"on":[17],"estimating":[18],"short-time":[19],"Fourier":[20],"transform":[21],"(STFT)":[22],"magnitude":[23],"discarding":[25],"phase":[26,35],"information.":[27],"We":[28],"observe":[29],"that,":[30],"singing":[32],"voice":[33,52,102],"separation,":[34],"can":[36],"make":[37],"considerable":[38],"improvement":[39],"in":[40],"quality.":[42],"This":[43],"paper":[44],"proposes":[45],"a":[46],"complex":[47],"ratio":[48],"masking":[49],"method":[50,58,94],"accompaniment":[54],"separation.":[55],"The":[56],"proposed":[57,93],"employs":[59],"DenseUNet":[60],"with":[61],"self":[62],"attention":[63],"to":[64,83],"estimate":[65],"the":[66,92],"real":[67],"imaginary":[69],"components":[70],"STFT":[72],"each":[74],"sound":[75],"source.":[76],"A":[77],"simple":[78],"ensemble":[79],"technique":[80],"introduced":[82],"further":[84],"improve":[85],"performance.":[87],"Evaluation":[88],"results":[89],"demonstrate":[90],"that":[91],"outperforms":[95],"recent":[96],"state-of-the-art":[97],"models":[98],"both":[100],"separated":[101],"accompaniment.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}