{"id":"https://openalex.org/W2920053118","doi":"https://doi.org/10.1109/acssc.2018.8645257","title":"Examining the Perceptual Effect of Alternative Objective Functions for Deep Learning Based Music Source Separation","display_name":"Examining the Perceptual Effect of Alternative Objective Functions for Deep Learning Based Music Source Separation","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2920053118","doi":"https://doi.org/10.1109/acssc.2018.8645257","mag":"2920053118"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2018.8645257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645257","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"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":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","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/A5044396558","display_name":"Stylianos Ioannis Mimilakis","orcid":"https://orcid.org/0000-0003-4633-5538"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stylianos Ioannis Mimilakis","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031086670","display_name":"Estefan\u00eda Cano","orcid":"https://orcid.org/0000-0002-1056-5844"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Estefania Cano","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027353739","display_name":"Derry Fitzgerald","orcid":"https://orcid.org/0000-0001-8057-858X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derry FitzGerald","raw_affiliation_strings":["AudioSourceRE, Cork, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AudioSourceRE, Cork, Ireland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087435726","display_name":"Gerald Schuller","orcid":"https://orcid.org/0000-0003-0591-4365"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerald Schuller","raw_affiliation_strings":["Technical University of Ilmenau, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Ilmenau, Ilmenau, Germany","institution_ids":["https://openalex.org/I119449181"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3608,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56726946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"679","last_page":"683"},"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":0.9995999932289124,"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":0.9983000159263611,"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/regularization","display_name":"Regularization (linguistics)","score":0.6727657914161682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.611375629901886},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5958253741264343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5868218541145325},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5707026720046997},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4773542881011963},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46511533856391907},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4538629353046417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45066559314727783},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4501662850379944},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39560770988464355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32536792755126953},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2723349630832672},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13912636041641235},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09876802563667297},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0700804591178894}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6727657914161682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.611375629901886},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5958253741264343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5868218541145325},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5707026720046997},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4773542881011963},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46511533856391907},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4538629353046417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45066559314727783},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4501662850379944},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39560770988464355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32536792755126953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2723349630832672},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13912636041641235},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09876802563667297},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0700804591178894},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acssc.2018.8645257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645257","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"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":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1519476818","https://openalex.org/W1600046928","https://openalex.org/W2115562708","https://openalex.org/W2127851351","https://openalex.org/W2130700490","https://openalex.org/W2137075158","https://openalex.org/W2408744528","https://openalex.org/W2563913346","https://openalex.org/W2565807767","https://openalex.org/W2595181260","https://openalex.org/W2620812332","https://openalex.org/W2746601360","https://openalex.org/W2783831488","https://openalex.org/W2791686384","https://openalex.org/W2796571515","https://openalex.org/W2810443465","https://openalex.org/W2886515811","https://openalex.org/W2889610689","https://openalex.org/W2891405874","https://openalex.org/W2962970934","https://openalex.org/W2963141945","https://openalex.org/W2963191020","https://openalex.org/W2963750251","https://openalex.org/W2963905071","https://openalex.org/W2963992487","https://openalex.org/W2964005873","https://openalex.org/W4285719527","https://openalex.org/W4298310324","https://openalex.org/W6630995465","https://openalex.org/W6635978488","https://openalex.org/W6731174860","https://openalex.org/W6734587955","https://openalex.org/W6744013906","https://openalex.org/W6746310539","https://openalex.org/W6747747266","https://openalex.org/W6752672694"],"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/W1501596003","https://openalex.org/W2077498359"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"examine":[4,61],"the":[5,14,32,53,67,104],"effect":[6],"of":[7,31,52],"various":[8,62],"objective":[9,39,97],"functions":[10],"used":[11],"to":[12,75],"optimize":[13],"recently":[15,81],"proposed":[16],"deep":[17],"learning":[18],"architecture":[19,34],"for":[20,83],"singing":[21,54,110],"voice":[22,111],"separation":[23,112],"MaD":[24,33],"-":[25],"Masker":[26],"and":[27,48,56,73,91,99],"Denoiser.":[28],"The":[29],"parameters":[30],"are":[35],"optimized":[36],"using":[37],"an":[38],"function":[40],"that":[41,103],"contains":[42],"a":[43,57],"reconstruction":[44,63],"criterion":[45],"between":[46],"predicted":[47],"true":[49],"magnitude":[50],"spectra":[51],"voice,":[55],"regularization":[58,86,106],"term.":[59],"We":[60,78],"criteria":[64],"such":[65,88],"as":[66,89],"generalized":[68],"Kullback-Leibler,":[69],"mean":[70],"squared":[71],"error,":[72],"noise":[74],"mask":[76],"ratio.":[77],"also":[79],"explore":[80],"proposed,":[82],"optimizing":[84],"MaD,":[85],"terms":[87],"sparsity":[90],"TwinNetwork":[92,105],"regularization.":[93],"Results":[94],"from":[95],"both":[96],"assessment":[98],"listening":[100],"tests":[101],"suggest":[102],"results":[107],"in":[108],"improved":[109],"quality.":[113]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
