{"id":"https://openalex.org/W4405974183","doi":"https://doi.org/10.1109/msp.2024.3415569","title":"Model-Based Deep Learning for Music Information Research: Leveraging diverse knowledge sources to enhance explainability, controllability, and resource efficiency","display_name":"Model-Based Deep Learning for Music Information Research: Leveraging diverse knowledge sources to enhance explainability, controllability, and resource efficiency","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4405974183","doi":"https://doi.org/10.1109/msp.2024.3415569"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2024.3415569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2024.3415569","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04611461v2/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["T&#x00E9;l&#x00E9;com Paris, Palaiseau, France"],"raw_orcid":"https://orcid.org/0000-0002-4960-0010","affiliations":[{"raw_affiliation_string":"T&#x00E9;l&#x00E9;com Paris, Palaiseau, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027789239","display_name":"Vincent Lostanlen","orcid":"https://orcid.org/0000-0003-0580-1651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Lostanlen","raw_affiliation_strings":["Centre National de la Recherche Scientifique, Nantes, France"],"raw_orcid":"https://orcid.org/0000-0003-0580-1651","affiliations":[{"raw_affiliation_string":"Centre National de la Recherche Scientifique, Nantes, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059890342","display_name":"Meinard M\u00fceller","orcid":"https://orcid.org/0000-0001-6062-7524"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6062-7524","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055423112"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5784,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91107454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"41","issue":"6","first_page":"51","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9891999959945679,"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/T11309","display_name":"Music and Audio Processing","score":0.9891999959945679,"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/controllability","display_name":"Controllability","score":0.8256597518920898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756482362747192},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5714641809463501},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5210142135620117},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5194898843765259},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.47381913661956787},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.46663910150527954},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44785526394844055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4331284761428833},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4046531021595001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846665322780609},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3274967074394226},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.12783074378967285},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12781265377998352},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12089589238166809},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09290885925292969}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.8256597518920898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756482362747192},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5714641809463501},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5210142135620117},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5194898843765259},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.47381913661956787},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.46663910150527954},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44785526394844055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4331284761428833},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4046531021595001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846665322780609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3274967074394226},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.12783074378967285},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12781265377998352},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12089589238166809},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09290885925292969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msp.2024.3415569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2024.3415569","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04611461v2","is_oa":true,"landing_page_url":"https://hal.science/hal-04611461","pdf_url":"https://hal.science/hal-04611461v2/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Magazine, 2024, 41 (6), &#x27E8;10.1109/MSP.2024.3415569&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04611461v2","is_oa":true,"landing_page_url":"https://hal.science/hal-04611461","pdf_url":"https://hal.science/hal-04611461v2/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Magazine, 2024, 41 (6), &#x27E8;10.1109/MSP.2024.3415569&#x27E9;","raw_type":"Journal articles"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G3848501275","display_name":null,"funder_award_id":"500643750","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4326088756","display_name":null,"funder_award_id":"101052978","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8749904681","display_name":null,"funder_award_id":"112-2222-E-002-005-MY2","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320873","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405974183.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2127566601","https://openalex.org/W2260437991","https://openalex.org/W2404176928","https://openalex.org/W2437181147","https://openalex.org/W2766291668","https://openalex.org/W2906564021","https://openalex.org/W3016027511","https://openalex.org/W3080857286","https://openalex.org/W3092879656","https://openalex.org/W3096709315","https://openalex.org/W3111213250","https://openalex.org/W3112170415","https://openalex.org/W3162289111","https://openalex.org/W3174257816","https://openalex.org/W3207925746","https://openalex.org/W3213549365","https://openalex.org/W4254155963","https://openalex.org/W4323064860","https://openalex.org/W4382239517","https://openalex.org/W4386589137","https://openalex.org/W4388691923","https://openalex.org/W4390745914","https://openalex.org/W4392902821","https://openalex.org/W4395471070","https://openalex.org/W6731397234","https://openalex.org/W6756859573","https://openalex.org/W6760571136","https://openalex.org/W6771763809","https://openalex.org/W6782757012","https://openalex.org/W6810677096","https://openalex.org/W6842632288","https://openalex.org/W6846246655"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W3097613282","https://openalex.org/W4285190997","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686"],"abstract_inverted_index":{"In":[0,52],"this":[1],"article,":[2],"we":[3,23],"investigate":[4],"the":[5,14,26,72,88,97],"notion":[6],"of":[7,16,74,90,99],"<italic":[8],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[9],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">model-based":[10],"deep":[11,29,45,92],"learning</i>":[12],"in":[13,94],"realm":[15],"music":[17,62,65],"information":[18],"research":[19],"(MIR).":[20],"Loosely":[21],"speaking,":[22],"refer":[24],"to":[25,59,86],"term":[27],"model-based":[28,91],"learning":[30,93],"for":[31,56],"approaches":[32],"that":[33],"combine":[34],"traditional":[35],"knowledge-based":[36],"methods":[37],"with":[38],"data-driven":[39],"techniques,":[40],"especially":[41],"those":[42],"based":[43],"on":[44],"learning,":[46],"within":[47],"a":[48],"differentiable":[49],"computing":[50],"framework.":[51],"music,":[53],"prior":[54],"knowledge":[55],"instance":[57],"related":[58],"sound":[60],"production,":[61],"perception":[63],"or":[64],"composition":[66],"theory":[67],"can":[68],"be":[69],"incorporated":[70],"into":[71],"design":[73],"neural":[75],"networks":[76],"and":[77,102],"associated":[78],"loss":[79],"functions.":[80],"We":[81],"outline":[82],"three":[83],"specific":[84],"scenarios":[85],"illustrate":[87],"application":[89],"MIR,":[95],"demonstrating":[96],"implementation":[98],"such":[100],"concepts":[101],"their":[103],"potential.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-01-02T00:00:00"}