{"id":"https://openalex.org/W2986673441","doi":"https://doi.org/10.23919/eusipco.2019.8902550","title":"Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures","display_name":"Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2986673441","doi":"https://doi.org/10.23919/eusipco.2019.8902550","mag":"2986673441"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902550","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","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/A5024461884","display_name":"Andreas Jansson","orcid":"https://orcid.org/0000-0001-6123-7886"},"institutions":[{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Jansson","raw_affiliation_strings":["City, University of London / Spotify Inc, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City, University of London / Spotify Inc, New York, USA","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019790225","display_name":"Rachel Bittner","orcid":"https://orcid.org/0000-0001-7757-2232"},"institutions":[{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel M. Bittner","raw_affiliation_strings":["Spotify Inc, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spotify Inc, New York, USA","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Ewert","raw_affiliation_strings":["Spotify Inc, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spotify Inc, London, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018493892","display_name":"Tillman Weyde","orcid":"https://orcid.org/0000-0001-8028-9905"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tillman Weyde","raw_affiliation_strings":["City, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City, University of London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9998999834060669,"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":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7576068639755249},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7321420907974243},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7125416994094849},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6777267456054688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6412304043769836},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.6408184766769409},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5589675307273865},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4815683364868164},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.43164923787117004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35768190026283264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1869843602180481},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14592623710632324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06945902109146118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576068639755249},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7321420907974243},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7125416994094849},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6777267456054688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6412304043769836},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.6408184766769409},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5589675307273865},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4815683364868164},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.43164923787117004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35768190026283264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1869843602180481},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14592623710632324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06945902109146118},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco.2019.8902550","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:23669","is_oa":false,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/t=2Ee=2Eweyde.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1496920063","https://openalex.org/W1821462560","https://openalex.org/W1901129140","https://openalex.org/W1964208564","https://openalex.org/W2118774185","https://openalex.org/W2127851351","https://openalex.org/W2130770109","https://openalex.org/W2161632835","https://openalex.org/W2166209411","https://openalex.org/W2296724634","https://openalex.org/W2344535577","https://openalex.org/W2403272360","https://openalex.org/W2407185622","https://openalex.org/W2773294482","https://openalex.org/W2774707525","https://openalex.org/W2788560150","https://openalex.org/W2804679033","https://openalex.org/W2911064732","https://openalex.org/W2962866891","https://openalex.org/W2963698842","https://openalex.org/W6796299864"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2150113039","https://openalex.org/W2807674213","https://openalex.org/W2077498359","https://openalex.org/W2986673441"],"abstract_inverted_index":{"Vocal":[0],"source":[1,17,45],"separation":[2,18,82],"and":[3,59,73],"fundamental":[4,28,34,61],"frequency":[5,29,35],"estimation":[6,30,98,115],"in":[7],"music":[8],"are":[9],"tightly":[10],"related":[11],"tasks.":[12],"The":[13],"outputs":[14],"of":[15,108],"vocal":[16,27,33,44,81],"systems":[19],"have":[20],"previously":[21],"been":[22,37],"used":[23,38],"as":[24,39],"inputs":[25],"to":[26,42],"systems;":[31],"conversely,":[32],"has":[36],"side":[40],"information":[41],"improve":[43],"separation.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,104],"propose":[51],"several":[52],"different":[53],"approaches":[54],"for":[55,70,96,116],"jointly":[56],"separating":[57],"vocals":[58],"estimating":[60],"frequency.":[62],"We":[63],"show":[64],"that":[65,74],"joint":[66,91],"learning":[67],"is":[68],"advantageous":[69],"these":[71],"tasks,":[72],"a":[75],"stacked":[76],"architecture":[77],"which":[78],"first":[79],"performs":[80],"outperforms":[83],"the":[84,89,100,106],"other":[85],"configurations":[86],"considered.":[87],"Furthermore,":[88],"best":[90],"model":[92],"achieves":[93],"state-of-the-art":[94],"results":[95],"vocal-fo":[97,114],"on":[99],"iKala":[101],"dataset.":[102],"Finally,":[103],"highlight":[105],"importance":[107],"performing":[109],"polyphonic,":[110],"rather":[111],"than":[112],"monophonic":[113],"many":[117],"real-world":[118],"cases.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}