{"id":"https://openalex.org/W1601892841","doi":"https://doi.org/10.1109/icassp.2015.7178002","title":"On automatic drum transcription using non-negative matrix deconvolution and itakura saito divergence","display_name":"On automatic drum transcription using non-negative matrix deconvolution and itakura saito divergence","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1601892841","doi":"https://doi.org/10.1109/icassp.2015.7178002","mag":"1601892841"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01261256","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065828059","display_name":"Axel R\u00f6ebel","orcid":"https://orcid.org/0000-0001-6136-4391"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Roebel","raw_affiliation_strings":["UMR 9912-IRCAM/UPMC/CNRS, Paris, France","UMR 9912 - IRCAM/UPMC/CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR 9912-IRCAM/UPMC/CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]},{"raw_affiliation_string":"UMR 9912 - IRCAM/UPMC/CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]},{"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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["UMR 9912-IRCAM/UPMC/CNRS, Paris, France","UMR 9912 - IRCAM/UPMC/CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR 9912-IRCAM/UPMC/CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]},{"raw_affiliation_string":"UMR 9912 - IRCAM/UPMC/CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062200666","display_name":"Marco Liuni","orcid":"https://orcid.org/0000-0001-6831-8259"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marco Liuni","raw_affiliation_strings":["UMR 9912-IRCAM/UPMC/CNRS, Paris, France","UMR 9912 - IRCAM/UPMC/CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR 9912-IRCAM/UPMC/CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]},{"raw_affiliation_string":"UMR 9912 - IRCAM/UPMC/CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105897582","display_name":"Mathieu Lagrangey","orcid":null},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Lagrangey","raw_affiliation_strings":["Ecole centrale de Nantes, Nantes, Pays de la Loire, FR","IRCCyN, CNRS, Ecole Centrale de Nantes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole centrale de Nantes, Nantes, Pays de la Loire, FR","institution_ids":["https://openalex.org/I100445878"]},{"raw_affiliation_string":"IRCCyN, CNRS, Ecole Centrale de Nantes, France","institution_ids":["https://openalex.org/I100445878","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"414","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"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/drum","display_name":"Drum","score":0.7496728897094727},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7334122657775879},{"id":"https://openalex.org/keywords/deconvolution","display_name":"Deconvolution","score":0.6959847807884216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6151793003082275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5192668437957764},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4796617329120636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39415064454078674},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37502580881118774},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.316989004611969},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21316561102867126},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11453476548194885},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07599776983261108}],"concepts":[{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.7496728897094727},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7334122657775879},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.6959847807884216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151793003082275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5192668437957764},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4796617329120636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39415064454078674},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37502580881118774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.316989004611969},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21316561102867126},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11453476548194885},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07599776983261108},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01261256v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01261256","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), Apr 2015, Brisbane, Australia. pp.414 - 418, &#x27E8;10.1109/ICASSP.2015.7178002&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01261256v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01261256","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), Apr 2015, Brisbane, Australia. pp.414 - 418, &#x27E8;10.1109/ICASSP.2015.7178002&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8900405670","display_name":"Hierarchical Object-based Unsupervised Learning for Computational Auditory Scene Analysis","funder_award_id":"ANR-11-JS03-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W80364729","https://openalex.org/W129413713","https://openalex.org/W192383697","https://openalex.org/W1519655822","https://openalex.org/W1603632465","https://openalex.org/W2039844283","https://openalex.org/W2075567905","https://openalex.org/W2096482524","https://openalex.org/W2097954800","https://openalex.org/W2103709905","https://openalex.org/W2106582496","https://openalex.org/W2114508388","https://openalex.org/W2129258718","https://openalex.org/W2168076624","https://openalex.org/W2403670595","https://openalex.org/W2403874381","https://openalex.org/W2483000653","https://openalex.org/W4298331807","https://openalex.org/W6603229298","https://openalex.org/W6607890289","https://openalex.org/W6631117800","https://openalex.org/W6636328019","https://openalex.org/W6674508888","https://openalex.org/W6676199445","https://openalex.org/W6712990308","https://openalex.org/W6713660056"],"related_works":["https://openalex.org/W2356237291","https://openalex.org/W2411659965","https://openalex.org/W2960896737","https://openalex.org/W2387677326","https://openalex.org/W2390208690","https://openalex.org/W4200063482","https://openalex.org/W2371365383","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2386180132"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"investigation":[4],"into":[5],"the":[6,25,46,72,84,108,112,131,135],"detection":[7,69,103,123],"and":[8,16,24,79,82,99,127],"classification":[9],"of":[10,86,111,134],"drum":[11,17,122,128],"sounds":[12,96],"in":[13,124],"polyphonic":[14,125],"music":[15,126],"loops":[18],"using":[19,71],"non-negative":[20],"matrix":[21],"deconvolution":[22],"(NMD)":[23],"Itakura":[26,30,73],"Saito":[27,31,74],"divergence.":[28],"The":[29,61],"divergence":[32,75],"has":[33,55],"recently":[34],"been":[35,58],"proposed":[36,98,136],"as":[37],"especially":[38],"appropriate":[39],"for":[40,66,93,121],"decomposing":[41],"audio":[42,67],"spectra":[43],"due":[44],"to":[45],"fact":[47],"that":[48,76],"it":[49,54],"is":[50,97,116],"scale":[51],"invariant,":[52],"but":[53],"not":[56],"yet":[57],"widely":[59],"adopted.":[60],"article":[62],"studies":[63],"new":[64,91,102],"contributions":[65],"event":[68],"methods":[70],"improve":[77],"efficiency":[78],"numerical":[80],"stability,":[81],"simplify":[83],"generation":[85],"target":[87,113],"pattern":[88],"sets.":[89],"A":[90],"approach":[92],"handling":[94],"background":[95],"moreover,":[100],"a":[101],"criteria":[104],"based":[105],"on":[106],"estimating":[107],"perceptual":[109],"presence":[110],"class":[114],"sources":[115],"introduced.":[117],"Experimental":[118],"results":[119],"obtained":[120],"soli":[129],"demonstrate":[130],"beneficial":[132],"effects":[133],"extensions.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
