{"id":"https://openalex.org/W3010665651","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023055","title":"Monaural Singing Voice Separation Using Fusion-Net with Time-Frequency Masking","display_name":"Monaural Singing Voice Separation Using Fusion-Net with Time-Frequency Masking","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010665651","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023055","mag":"3010665651"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023055","is_oa":false,"landing_page_url":"http://doi.org/10.1109/apsipaasc47483.2019.9023055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100448828","display_name":"Feng Li","orcid":"https://orcid.org/0000-0001-7633-7863"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Feng Li","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, Japan 923-1292"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, Japan 923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030425371","display_name":"Kaizhi Qian","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":"Kaizhi Qian","raw_affiliation_strings":["[Beckman Institute, University of Illinois at Urbana-Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"[Beckman Institute, University of Illinois at Urbana-Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"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":"Mark Hasegawa-Johnson","raw_affiliation_strings":["[Beckman Institute, University of Illinois at Urbana-Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"[Beckman Institute, University of Illinois at Urbana-Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, Japan 923-1292"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, Japan 923-1292","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100448828"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1934993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1239","last_page":"1243"},"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/T11309","display_name":"Music 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":0.9977999925613403,"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/monaural","display_name":"Monaural","score":0.9427338242530823},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7980821132659912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7213605642318726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6135016083717346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5369332432746887},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5363131165504456},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.523060142993927},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4712401032447815},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4529028832912445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3402627110481262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3350416421890259},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2133883833885193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1527387797832489},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11714014410972595}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9427338242530823},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7980821132659912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213605642318726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6135016083717346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5369332432746887},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5363131165504456},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.523060142993927},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4712401032447815},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4529028832912445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3402627110481262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3350416421890259},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2133883833885193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1527387797832489},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11714014410972595},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023055","is_oa":false,"landing_page_url":"http://doi.org/10.1109/apsipaasc47483.2019.9023055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/16658","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/16658","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1580974668","https://openalex.org/W1842657353","https://openalex.org/W2015276542","https://openalex.org/W2018735295","https://openalex.org/W2022668263","https://openalex.org/W2038678505","https://openalex.org/W2053165762","https://openalex.org/W2062710265","https://openalex.org/W2098950531","https://openalex.org/W2116244429","https://openalex.org/W2127851351","https://openalex.org/W2150415460","https://openalex.org/W2158216966","https://openalex.org/W2164098335","https://openalex.org/W2169327228","https://openalex.org/W2221409856","https://openalex.org/W2403623315","https://openalex.org/W2582996697","https://openalex.org/W2587994092","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2903502793","https://openalex.org/W2916583660","https://openalex.org/W2916985722","https://openalex.org/W2937391674","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W4249230140","https://openalex.org/W6631190155","https://openalex.org/W6713353306","https://openalex.org/W6732781371","https://openalex.org/W6746914816"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W1964208564","https://openalex.org/W169038075","https://openalex.org/W3214716754","https://openalex.org/W1976239252","https://openalex.org/W1614994442","https://openalex.org/W2035580387"],"abstract_inverted_index":{"Monaural":[0],"singing":[1,23,76],"voice":[2,24,77],"separation":[3,58,92],"has":[4],"received":[5],"much":[6,40],"attention":[7],"in":[8],"recent":[9],"years.":[10],"In":[11,49],"this":[12],"paper,":[13],"we":[14,51,61],"propose":[15],"a":[16,39],"novel":[17],"neural":[18,35,42],"network":[19,36,43],"architecture":[20,44,98],"for":[21],"monaural":[22],"separation,":[25],"Fusion-Net,":[26],"which":[27],"is":[28],"combining":[29],"U-Net":[30,97],"with":[31,45,66],"the":[32,57,63,70,74,79,86,95,100],"residual":[33],"convolutional":[34],"to":[37,55,72],"develop":[38],"deeper":[41],"summation-based":[46],"skip":[47],"connections.":[48],"addition,":[50],"apply":[52],"time-frequency":[53],"masking":[54],"improve":[56],"results.":[59],"Finally,":[60],"integrate":[62],"phase":[64],"spectra":[65,68],"magnitude":[67],"as":[69],"post-processing":[71],"optimize":[73],"separated":[75],"from":[78],"mixture":[80],"music.":[81],"Experimental":[82],"results":[83],"demonstrate":[84],"that":[85],"proposed":[87],"method":[88],"can":[89],"achieve":[90],"better":[91],"performance":[93],"than":[94],"previous":[96],"on":[99],"ccMixter":[101],"database.":[102]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}