{"id":"https://openalex.org/W3094480707","doi":"https://doi.org/10.1109/icassp39728.2021.9413358","title":"Transcription Is All You Need: Learning To Separate Musical Mixtures With Score As Supervision","display_name":"Transcription Is All You Need: Learning To Separate Musical Mixtures With Score As Supervision","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3094480707","doi":"https://doi.org/10.1109/icassp39728.2021.9413358","mag":"3094480707"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/2010.11904","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","Mitsubishi Electric Research Laboratories,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,#TAB#","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","Mitsubishi Electric Research Laboratories,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,#TAB#","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"46","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6282925009727478},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6274553537368774},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6270633339881897},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6125996112823486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4514731764793396},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.45038771629333496},{"id":"https://openalex.org/keywords/instrumental-music","display_name":"Instrumental music","score":0.4208180904388428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40987828373908997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39312493801116943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6282925009727478},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6274553537368774},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6270633339881897},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6125996112823486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514731764793396},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.45038771629333496},{"id":"https://openalex.org/C2993931450","wikidata":"https://www.wikidata.org/wiki/Q639197","display_name":"Instrumental music","level":3,"score":0.4208180904388428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40987828373908997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39312493801116943},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11904","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11904","pdf_url":"https://arxiv.org/pdf/2010.11904","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":"mag:3094480707","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.11904","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.11904","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11904","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":"Preprint"},{"id":"doi:10.17023/qfv1-8r34","is_oa":true,"landing_page_url":"https://doi.org/10.17023/qfv1-8r34","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:2010.11904","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11904","pdf_url":"https://arxiv.org/pdf/2010.11904","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094480707.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1556219185","https://openalex.org/W2107328928","https://openalex.org/W2124539664","https://openalex.org/W2253434170","https://openalex.org/W2296724634","https://openalex.org/W2402588270","https://openalex.org/W2475687244","https://openalex.org/W2523056285","https://openalex.org/W2560254426","https://openalex.org/W2593116425","https://openalex.org/W2764251778","https://openalex.org/W2792764867","https://openalex.org/W2800600340","https://openalex.org/W2898963093","https://openalex.org/W2899260162","https://openalex.org/W2903718461","https://openalex.org/W2952218014","https://openalex.org/W2962865004","https://openalex.org/W2963406748","https://openalex.org/W2963493667","https://openalex.org/W2963933499","https://openalex.org/W2964058413","https://openalex.org/W2964159544","https://openalex.org/W2964229681","https://openalex.org/W2984935418","https://openalex.org/W2988200020","https://openalex.org/W2990666817","https://openalex.org/W2997987128","https://openalex.org/W2998490864","https://openalex.org/W3004910802","https://openalex.org/W3015213533","https://openalex.org/W3104704316","https://openalex.org/W6691781196","https://openalex.org/W6697040288","https://openalex.org/W6714030504","https://openalex.org/W6721020019","https://openalex.org/W6727368055","https://openalex.org/W6730401039","https://openalex.org/W6734260513","https://openalex.org/W6745457739","https://openalex.org/W6745704996","https://openalex.org/W6749825310","https://openalex.org/W6750599028","https://openalex.org/W6766320909"],"related_works":["https://openalex.org/W2951472531","https://openalex.org/W3037831250","https://openalex.org/W2949361302","https://openalex.org/W2964317478","https://openalex.org/W2991108091","https://openalex.org/W3092835774","https://openalex.org/W2767272365","https://openalex.org/W3100093612","https://openalex.org/W2954886595","https://openalex.org/W2986341143","https://openalex.org/W2020954089","https://openalex.org/W3153597994","https://openalex.org/W2990928202","https://openalex.org/W2986773982","https://openalex.org/W3091791101","https://openalex.org/W3020987135","https://openalex.org/W2553022200","https://openalex.org/W3030187020","https://openalex.org/W3176829883","https://openalex.org/W3111558796"],"abstract_inverted_index":{"Most":[0],"music":[1],"source":[2,39],"separation":[3,40,47,154],"systems":[4],"require":[5,53],"large":[6],"collections":[7],"of":[8,72,101,113,129],"isolated":[9,54],"sources":[10],"for":[11,36,67,80,126],"training,":[12,118],"which":[13,26],"can":[14],"be":[15],"difficult":[16],"to":[17,30,97,149],"obtain.":[18],"In":[19,42],"this":[20],"work,":[21],"we":[22,120],"use":[23],"musical":[24],"scores,":[25],"are":[27],"comparatively":[28],"easy":[29],"obtain,":[31],"as":[32,61,88,110],"a":[33,38,62,73,77,84,89],"weak":[34],"label":[35],"training":[37,63],"system.":[41],"contrast":[43],"with":[44],"previous":[45],"score-informed":[46],"approaches,":[48],"our":[49],"system":[50],"does":[51],"not":[52,65],"sources,":[55],"and":[56,83,94,119,133,145,155],"score":[57,115,140],"is":[58,108],"used":[59],"only":[60],"target,":[64],"required":[66],"inference.":[68],"Our":[69],"model":[70],"consists":[71],"separator":[74],"that":[75,86,138],"outputs":[76],"time-frequency":[78],"mask":[79,106],"each":[81],"instrument,":[82],"transcriptor":[85,132],"acts":[87],"critic,":[90],"providing":[91],"both":[92,130,153],"temporal":[93,143],"frequency":[95],"supervision":[96],"guide":[98],"the":[99,102,131,134],"learning":[100],"separator.":[103,135],"A":[104],"harmonic":[105],"constraint":[107],"introduced":[109],"another":[111],"way":[112],"leveraging":[114],"information":[116,141],"during":[117],"propose":[121],"two":[122],"novel":[123],"adversarial":[124,146],"losses":[125],"additional":[127],"fine-tuning":[128],"Results":[136],"demonstrate":[137],"using":[139],"outper-forms":[142],"weak-labels,":[144],"structures":[147],"lead":[148],"further":[150],"improvements":[151],"in":[152],"transcription":[156],"performance.":[157]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}