{"id":"https://openalex.org/W2981713629","doi":"https://doi.org/10.1109/icassp40776.2020.9054340","title":"Simultaneous Separation and Transcription of Mixtures with Multiple Polyphonic and Percussive Instruments","display_name":"Simultaneous Separation and Transcription of Mixtures with Multiple Polyphonic and Percussive Instruments","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981713629","doi":"https://doi.org/10.1109/icassp40776.2020.9054340","mag":"2981713629"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054340","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.12621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023355857","display_name":"Ethan Manilow","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ethan Manilow","raw_affiliation_strings":["Interactive Audio Lab, Northwestern University, Evanston, IL, USA","Northwestern University,Interactive Audio Lab,Evanston,IL,USA"],"affiliations":[{"raw_affiliation_string":"Interactive Audio Lab, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University,Interactive Audio Lab,Evanston,IL,USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023673004","display_name":"Prem Seetharaman","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Seetharaman","raw_affiliation_strings":["Interactive Audio Lab, Northwestern University, Evanston, IL, USA","Northwestern University,Interactive Audio Lab,Evanston,IL,USA"],"affiliations":[{"raw_affiliation_string":"Interactive Audio Lab, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University,Interactive Audio Lab,Evanston,IL,USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Interactive Audio Lab, Northwestern University, Evanston, IL, USA","Northwestern University,Interactive Audio Lab,Evanston,IL,USA"],"affiliations":[{"raw_affiliation_string":"Interactive Audio Lab, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University,Interactive Audio Lab,Evanston,IL,USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023355857"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.6095,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64699339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"771","last_page":"775"},"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":0.9973999857902527,"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/polyphony","display_name":"Polyphony","score":0.8047021627426147},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6655506491661072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6329798698425293},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6168747544288635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4469694495201111},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.4456021189689636},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44447198510169983},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42422398924827576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3468804359436035},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.13059261441230774},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09893792867660522},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.08846470713615417}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8047021627426147},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6655506491661072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6329798698425293},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6168747544288635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4469694495201111},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.4456021189689636},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44447198510169983},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42422398924827576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3468804359436035},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.13059261441230774},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09893792867660522},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08846470713615417},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054340","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:arXiv.org:1910.12621","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12621","pdf_url":"https://arxiv.org/pdf/1910.12621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.1910.12621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.12621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"doi:10.17023/tkw0-3748","is_oa":true,"landing_page_url":"https://doi.org/10.17023/tkw0-3748","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"article"},{"id":"mag:2981713629","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.12621","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12621","pdf_url":"https://arxiv.org/pdf/1910.12621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981713629.pdf","grobid_xml":"https://content.openalex.org/works/W2981713629.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2017548439","https://openalex.org/W2059443479","https://openalex.org/W2092781592","https://openalex.org/W2105143211","https://openalex.org/W2110007838","https://openalex.org/W2113217465","https://openalex.org/W2221409856","https://openalex.org/W2552071709","https://openalex.org/W2624871570","https://openalex.org/W2766393356","https://openalex.org/W2899260162","https://openalex.org/W2902076983","https://openalex.org/W2964058413","https://openalex.org/W2986673441","https://openalex.org/W2998490864","https://openalex.org/W3015542311","https://openalex.org/W6714030504","https://openalex.org/W6739365718","https://openalex.org/W6745851314","https://openalex.org/W6756341328","https://openalex.org/W6769845053","https://openalex.org/W6775477063"],"related_works":["https://openalex.org/W3121270467","https://openalex.org/W3187921808","https://openalex.org/W3122606659","https://openalex.org/W3091253170","https://openalex.org/W3114975468","https://openalex.org/W2771644120","https://openalex.org/W3160751854","https://openalex.org/W3098670224","https://openalex.org/W2273352734","https://openalex.org/W3135022317","https://openalex.org/W2344815408","https://openalex.org/W2399539226","https://openalex.org/W1998139849","https://openalex.org/W2921244131","https://openalex.org/W2184350756","https://openalex.org/W2604244390","https://openalex.org/W2981402174","https://openalex.org/W3083006538","https://openalex.org/W3189624906","https://openalex.org/W2017416504"],"abstract_inverted_index":{"We":[0,90],"present":[1],"a":[2,15,27,35,59,87],"single":[3,88],"deep":[4],"learning":[5,34],"architecture":[6],"that":[7,92,110],"can":[8],"both":[9,40,114],"separate":[10,79],"an":[11],"audio":[12],"recording":[13],"of":[14],"musical":[16,37],"mixture":[17],"into":[18,26],"constituent":[19],"single-instrument":[20],"recordings":[21],"and":[22,80,94,102,116,118],"transcribe":[23,81],"these":[24],"instruments":[25,85],"human-readable":[28],"format":[29],"at":[30,113],"the":[31,51],"same":[32],"time,":[33],"shared":[36],"representation":[38],"for":[39,54,62],"tasks.":[41],"This":[42],"novel":[43],"architecture,":[44],"which":[45],"we":[46,71],"call":[47],"Cerberus,":[48],"builds":[49],"on":[50],"Chimera":[52],"network":[53],"source":[55],"separation":[56,93,115],"by":[57],"adding":[58],"third":[60],"\"head\"":[61],"transcription.":[63],"By":[64],"training":[65],"each":[66],"head":[67],"with":[68,86,99],"different":[69],"losses,":[70],"are":[72,96,111],"able":[73],"to":[74,78,83,107,121],"jointly":[75],"learn":[76],"how":[77],"up":[82],"five":[84],"network.":[89],"show":[91],"transcription":[95,117],"highly":[97],"complementary":[98],"one":[100],"another":[101],"when":[103],"learned":[104],"jointly,":[105],"lead":[106],"Cerberus":[108],"networks":[109],"better":[112,120],"generalize":[119],"unseen":[122],"mixtures.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-28T00:00:00"}
