{"id":"https://openalex.org/W2767764538","doi":"https://doi.org/10.1109/icassp.2018.8461822","title":"Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask","display_name":"Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2767764538","doi":"https://doi.org/10.1109/icassp.2018.8461822","mag":"2767764538"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.01437","any_repository_has_fulltext":true},"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/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"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":["Tampere University of Technology, Tampere, Finland","Tampere university of technology, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere university of technology, Tampere, Finland","institution_ids":["https://openalex.org/I150589677","https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068457267","display_name":"Jo\u00e3o Felipe Santos","orcid":"https://orcid.org/0000-0003-3934-3943"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joao F. Santos","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada","Universit\u00e9 de Montr\u00e9al., Montr\u00e9al, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al., Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087435726","display_name":"Gerald Schuller","orcid":"https://orcid.org/0000-0003-0591-4365"},"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":"Gerald Schuller","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/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"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":"Tuomas Virtanen","raw_affiliation_strings":["Tampere University of Technology, Tampere, Finland","Tampere university of technology, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere university of technology, Tampere, Finland","institution_ids":["https://openalex.org/I150589677","https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada","Universit\u00e9 de Montr\u00e9al., Montr\u00e9al, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al., Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1808,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.29855147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1505 387","issue":null,"first_page":"721","last_page":"725"},"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":0.9987000226974487,"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":0.9962000250816345,"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":0.8930027484893799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7319245338439941},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6433144211769104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.601593554019928},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5566471815109253},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5182309150695801},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5152833461761475},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4994826316833496},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4975114166736603},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48839133977890015},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.45481929183006287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44341519474983215},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.4368789494037628},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43558192253112793},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.42338818311691284},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.42199862003326416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37211230397224426},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1713976263999939},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14217397570610046},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13610699772834778},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07460257411003113},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07205712795257568}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8930027484893799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319245338439941},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6433144211769104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.601593554019928},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5566471815109253},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5182309150695801},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5152833461761475},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4994826316833496},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4975114166736603},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48839133977890015},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.45481929183006287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44341519474983215},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.4368789494037628},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43558192253112793},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.42338818311691284},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.42199862003326416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37211230397224426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1713976263999939},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14217397570610046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13610699772834778},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07460257411003113},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07205712795257568},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2018.8461822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1711.01437","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.01437","pdf_url":"https://arxiv.org/pdf/1711.01437","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2767764538","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1711.01437","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:fraunhofer.de:N-520118","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-520118.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/403230","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/403230","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.1711.01437","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.01437","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.01437","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.01437","pdf_url":"https://arxiv.org/pdf/1711.01437","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2767764538.pdf","grobid_xml":"https://content.openalex.org/works/W2767764538.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1529883046","https://openalex.org/W1533861849","https://openalex.org/W1594771616","https://openalex.org/W1790748249","https://openalex.org/W2120847449","https://openalex.org/W2125930537","https://openalex.org/W2179490238","https://openalex.org/W2296724634","https://openalex.org/W2398306137","https://openalex.org/W2525778437","https://openalex.org/W2563534197","https://openalex.org/W2587994092","https://openalex.org/W2916985722","https://openalex.org/W2949892913","https://openalex.org/W2953267151","https://openalex.org/W2963141945","https://openalex.org/W2963197835","https://openalex.org/W2963750251","https://openalex.org/W3038058348","https://openalex.org/W4285719527","https://openalex.org/W6604406162","https://openalex.org/W6631943919","https://openalex.org/W6680067488","https://openalex.org/W6685863848","https://openalex.org/W6697040288","https://openalex.org/W6712656540","https://openalex.org/W6724411756","https://openalex.org/W6733667431","https://openalex.org/W6734587955","https://openalex.org/W6759212570"],"related_works":["https://openalex.org/W2964005873","https://openalex.org/W2753623599","https://openalex.org/W2894785362","https://openalex.org/W1999736059","https://openalex.org/W3094387658","https://openalex.org/W2798722646","https://openalex.org/W2408394826","https://openalex.org/W3128223806","https://openalex.org/W3045520545","https://openalex.org/W2918711952","https://openalex.org/W2057826000","https://openalex.org/W2937626622","https://openalex.org/W1999555840","https://openalex.org/W3010851250","https://openalex.org/W2941484407","https://openalex.org/W2718052359","https://openalex.org/W3162493033","https://openalex.org/W2573611911","https://openalex.org/W2921144622","https://openalex.org/W2574422787"],"abstract_inverted_index":{"Singing":[0],"voice":[1,126],"separation":[2],"based":[3],"on":[4,8,41],"deep":[5,31],"learning":[6,32],"relies":[7],"the":[9,17,30,37,47,69,86,104,113],"usage":[10],"of":[11,36,100],"time-frequency":[12],"masking.":[13],"In":[14],"many":[15],"cases":[16],"masking":[18],"process":[19],"is":[20,26],"not":[21,27,67],"a":[22,42,54,62,76,80,91],"learnable":[23],"function":[24],"or":[25],"encapsulated":[28],"into":[29],"optimization.":[33],"Consequently,":[34],"most":[35],"existing":[38],"methods":[39],"rely":[40],"post":[43,71],"processing":[44,72],"step":[45,83],"using":[46],"generalized":[48],"Wiener":[49],"filtering.":[50],"This":[51],"work":[52],"proposes":[53],"method":[55],"that":[56],"learns":[57],"and":[58,65,90,109],"optimizes":[59],"(during":[60],"training)":[61],"source-dependent":[63],"mask":[64,87],"does":[66],"need":[68],"aforementioned":[70],"step.":[73],"We":[74],"introduce":[75],"recurrent":[77],"inference":[78],"algorithm,":[79],"sparse":[81],"transformation":[82],"to":[84,106,115,119],"improve":[85],"generation":[88],"process,":[89],"learned":[92],"denoising":[93],"filter.":[94],"Obtained":[95],"results":[96],"show":[97],"an":[98],"increase":[99],"0.49":[101],"dB":[102,111],"for":[103,112,123],"signal":[105,114],"distortion":[107],"ratio":[108],"0.30":[110],"interference":[116],"ratio,":[117],"compared":[118],"previous":[120],"state-of-the-art":[121],"approaches":[122],"monaural":[124],"singing":[125],"separation.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}