{"id":"https://openalex.org/W2898606530","doi":"https://doi.org/10.21437/interspeech.2019-1177","title":"End-to-End Music Source Separation: Is it Possible in the Waveform Domain?","display_name":"End-to-End Music Source Separation: Is it Possible in the Waveform Domain?","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2898606530","doi":"https://doi.org/10.21437/interspeech.2019-1177","mag":"2898606530"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1810.12187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084549869","display_name":"Francesc Llu\u00eds","orcid":"https://orcid.org/0000-0002-8994-5558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesc Llu\u00eds","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"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 Pons","raw_affiliation_strings":["Pompeu Fabra University, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"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":"Xavier Serra","raw_affiliation_strings":["Pompeu Fabra Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra Univ","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1027,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87323226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4619","last_page":"4623"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9564812183380127},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.8089868426322937},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7425544857978821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6898647546768188},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6161189079284668},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5848767757415771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49574026465415955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46623489260673523},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45790788531303406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3463493585586548},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33482348918914795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2266896665096283},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15247425436973572}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9564812183380127},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.8089868426322937},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7425544857978821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898647546768188},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6161189079284668},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5848767757415771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49574026465415955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46623489260673523},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45790788531303406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3463493585586548},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33482348918914795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2266896665096283},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15247425436973572},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-1177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1810.12187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.12187","pdf_url":"https://arxiv.org/pdf/1810.12187","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":null,"raw_type":"text"},{"id":"pmh:oai:repositori.upf.edu:10230/47239","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/47239","pdf_url":"https://repositori.upf.edu/bitstreams/7dc289bb-ec8a-4b16-9737-10b483d04304/download","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"mag:2898606530","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.12187.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.1810.12187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.12187","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:1810.12187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.12187","pdf_url":"https://arxiv.org/pdf/1810.12187","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W178436704","https://openalex.org/W1529551391","https://openalex.org/W1601892841","https://openalex.org/W1901129140","https://openalex.org/W1943178216","https://openalex.org/W2105464873","https://openalex.org/W2123649031","https://openalex.org/W2155355606","https://openalex.org/W2157266364","https://openalex.org/W2163312093","https://openalex.org/W2405258286","https://openalex.org/W2583165630","https://openalex.org/W2587994092","https://openalex.org/W2604509013","https://openalex.org/W2614024025","https://openalex.org/W2654729393","https://openalex.org/W2766712974","https://openalex.org/W2769810959","https://openalex.org/W2774707525","https://openalex.org/W2777302760","https://openalex.org/W2894649632","https://openalex.org/W2894785362","https://openalex.org/W2916985722","https://openalex.org/W2949382160","https://openalex.org/W2962813390","https://openalex.org/W2962935966","https://openalex.org/W2963232038","https://openalex.org/W2963452667","https://openalex.org/W2963519193","https://openalex.org/W2963992487","https://openalex.org/W3143596294"],"related_works":["https://openalex.org/W2898145319","https://openalex.org/W2964121744","https://openalex.org/W2963452667","https://openalex.org/W2990594533","https://openalex.org/W3099662743","https://openalex.org/W2467756818","https://openalex.org/W3179030250","https://openalex.org/W3015721817","https://openalex.org/W2798944765","https://openalex.org/W338534183","https://openalex.org/W3163618433","https://openalex.org/W178436704","https://openalex.org/W3183233282","https://openalex.org/W2980624499","https://openalex.org/W3163082873","https://openalex.org/W2782386721","https://openalex.org/W3104704316","https://openalex.org/W2279140676","https://openalex.org/W3177975252","https://openalex.org/W2506553484"],"abstract_inverted_index":{"Most":[0],"of":[1,21,36],"the":[2,9,22,24,34,50,54,59,63],"currently":[3],"successful":[4],"source":[5,42,68],"separation":[6,43,69],"techniques":[7],"use":[8],"magnitude":[10],"spectrogram":[11],"as":[12],"input,":[13],"and":[14,99],"are":[15],"therefore":[16],"by":[17],"default":[18],"omitting":[19,28],"part":[20],"signal:":[23],"phase.":[25,60],"To":[26],"avoid":[27],"potentially":[29],"useful":[30],"information,":[31],"we":[32,97],"study":[33],"viability":[35],"using":[37],"end-to-end":[38,66],"models":[39,80],"for":[40],"music":[41,67],"---":[44],"which":[45],"take":[46],"into":[47],"account":[48],"all":[49],"information":[51],"available":[52],"in":[53],"raw":[55],"audio":[56],"signal,":[57],"including":[58],"Although":[61],"during":[62],"last":[64],"decades":[65],"has":[70],"been":[71],"considered":[72],"almost":[73],"unattainable,":[74],"our":[75],"results":[76],"confirm":[77],"that":[78],"waveform-based":[79],"can":[81,101],"perform":[82],"similarly":[83],"(if":[84],"not":[85],"better)":[86],"than":[87],"a":[88,94,104],"spectrogram-based":[89,106],"deep":[90,107],"learning":[91,108],"model.":[92,109],"Namely:":[93],"Wavenet-based":[95],"model":[96],"propose":[98],"Wave-U-Net":[100],"outperform":[102],"DeepConvSep,":[103],"recent":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}