{"id":"https://openalex.org/W3005745421","doi":"https://doi.org/10.1109/icassp40776.2020.9053024","title":"Content Based Singing Voice Extraction from a Musical Mixture","display_name":"Content Based Singing Voice Extraction from a Musical Mixture","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005745421","doi":"https://doi.org/10.1109/icassp40776.2020.9053024","mag":"3005745421"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/2002.04933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019814087","display_name":"Pritish Chandna","orcid":"https://orcid.org/0000-0003-4784-7869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pritish Chandna","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005810332","display_name":"Merlijn Blaauw","orcid":"https://orcid.org/0000-0001-8051-9942"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Merlijn Blaauw","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060417258","display_name":"Jordi Bonada","orcid":"https://orcid.org/0000-0002-8671-0729"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Bonada","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027977314","display_name":"Em\u00edlia G\u00f3mez","orcid":"https://orcid.org/0000-0003-4983-3989"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Emilia Gomez","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, SPAIN","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.013267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"781","last_page":"785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/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":0.9995999932289124,"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":0.7236549854278564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6215760707855225},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5813286304473877},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5454556941986084},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5391702055931091},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5259045362472534},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5090577006340027},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4879121482372284},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4655856192111969},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4576647877693176},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4468829333782196},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4335106611251831},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4278145432472229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41804271936416626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3337953984737396},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09714215993881226},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08065146207809448},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07879936695098877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236549854278564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6215760707855225},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5813286304473877},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5454556941986084},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5391702055931091},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5259045362472534},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5090577006340027},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4879121482372284},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4655856192111969},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4576647877693176},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4468829333782196},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4335106611251831},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4278145432472229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41804271936416626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3337953984737396},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09714215993881226},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08065146207809448},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07879936695098877},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/46456","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/46456","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2002.04933","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04933","pdf_url":"https://arxiv.org/pdf/2002.04933","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":"","raw_type":"text"},{"id":"mag:3005745421","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.04933.pdf","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":"doi:10.48550/arxiv.2002.04933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.04933","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":"article-journal"},{"id":"doi:10.17023/f07s-5y20","is_oa":true,"landing_page_url":"https://doi.org/10.17023/f07s-5y20","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.04933","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04933","pdf_url":"https://arxiv.org/pdf/2002.04933","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2098446659","https://openalex.org/W2099741732","https://openalex.org/W2164098335","https://openalex.org/W2296704011","https://openalex.org/W2296724634","https://openalex.org/W2405258286","https://openalex.org/W2471520273","https://openalex.org/W2532494225","https://openalex.org/W2563534197","https://openalex.org/W2587994092","https://openalex.org/W2752796333","https://openalex.org/W2774707525","https://openalex.org/W2778460379","https://openalex.org/W2795409001","https://openalex.org/W2796010067","https://openalex.org/W2909169132","https://openalex.org/W2921904817","https://openalex.org/W2943667773","https://openalex.org/W2949281321","https://openalex.org/W2962935966","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2972970915","https://openalex.org/W2986673441","https://openalex.org/W6674722923","https://openalex.org/W6697040288","https://openalex.org/W6697285287","https://openalex.org/W6713676406","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W3015268063","https://openalex.org/W3009039098","https://openalex.org/W2921244131","https://openalex.org/W3015225476","https://openalex.org/W3192255518","https://openalex.org/W581487149","https://openalex.org/W2398291266","https://openalex.org/W3048203730","https://openalex.org/W1969077401","https://openalex.org/W1580780811","https://openalex.org/W3109050852","https://openalex.org/W2562176306","https://openalex.org/W2342978468","https://openalex.org/W2964819890","https://openalex.org/W2184350756","https://openalex.org/W3083127","https://openalex.org/W1499139979","https://openalex.org/W3095436719","https://openalex.org/W2516392987","https://openalex.org/W3174257816"],"abstract_inverted_index":{"We":[0,135],"present":[1],"a":[2,14,40,57,62,92],"deep":[3,129],"learning":[4,130],"based":[5,17,131],"methodology":[6,126],"for":[7,91,143],"extracting":[8],"the":[9,19,33,37,49,70,82,88,103,125],"singing":[10],"voice":[11],"signal":[12,86],"from":[13,87],"musical":[15,41],"mixture":[16,42,89,94],"on":[18],"underlying":[20],"linguistic":[21],"content.":[22],"Our":[23],"model":[24,50],"follows":[25],"an":[26],"encoder-decoder":[27],"architecture":[28],"and":[29,140],"takes":[30],"as":[31],"input":[32],"magnitude":[34],"component":[35],"of":[36,39,48,105],"spectrogram":[38],"with":[43,96,111],"vocals.":[44],"The":[45],"encoder":[46],"part":[47],"is":[51,66],"trained":[52],"via":[53,120],"knowledge":[54],"distillation":[55],"using":[56],"teacher":[58],"network":[59],"to":[60,68,80,123,127],"learn":[61],"content":[63],"embedding,":[64],"which":[65],"decoded":[67],"generate":[69],"corresponding":[71],"vocoder":[72],"features.":[73],"Using":[74],"this":[75],"methodology,":[76],"we":[77,116],"are":[78],"able":[79],"extract":[81],"unprocessed":[83],"raw":[84],"vocal":[85],"even":[90],"processed":[93],"dataset":[95],"singers":[97],"not":[98],"seen":[99],"during":[100],"training.":[101],"While":[102],"nature":[104],"our":[106],"system":[107],"makes":[108],"it":[109],"incongruous":[110],"traditional":[112],"objective":[113],"evaluation":[114,119],"metrics,":[115],"use":[117],"subjective":[118],"listening":[121],"tests":[122],"compare":[124],"state-of-the-art":[128],"source":[132,141],"separation":[133],"algorithms.":[134],"also":[136],"provide":[137],"sound":[138],"examples":[139],"code":[142],"reproducibility.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}