{"id":"https://openalex.org/W4205402425","doi":"https://doi.org/10.23919/eusipco54536.2021.9616031","title":"Predominant Jazz Instrument Recognition: Empirical Studies on Neural Network Architectures","display_name":"Predominant Jazz Instrument Recognition: Empirical Studies on Neural Network Architectures","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205402425","doi":"https://doi.org/10.23919/eusipco54536.2021.9616031"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616031","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616031","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112610897","display_name":"Jakob Abeber","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jakob Abeber","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062766360","display_name":"Jaydeep Chauhan","orcid":"https://orcid.org/0000-0003-1592-4436"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jaydeep Chauhan","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058850903","display_name":"Prateek Pradeep Pillai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Prateek Pradeep Pillai","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022729641","display_name":"Michael Taenzer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Taenzer","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044396558","display_name":"Stylianos Ioannis Mimilakis","orcid":"https://orcid.org/0000-0003-4633-5538"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stylianos I. Mimilakis","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112610897"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":0.172,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39959704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"365"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/jazz","display_name":"Jazz","score":0.8589872121810913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7609378695487976},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6318439245223999},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5985463857650757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5807616710662842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5153524279594421},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4944605827331543},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4683018922805786},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4587955176830292},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4500768184661865},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4132493734359741},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3614651560783386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3512028455734253}],"concepts":[{"id":"https://openalex.org/C2980749","wikidata":"https://www.wikidata.org/wiki/Q8341","display_name":"Jazz","level":2,"score":0.8589872121810913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609378695487976},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6318439245223999},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5985463857650757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5807616710662842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5153524279594421},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4944605827331543},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4683018922805786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4587955176830292},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4500768184661865},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4132493734359741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614651560783386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3512028455734253},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616031","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616031","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-648014","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-648014.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/417263","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/417263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7794680673","display_name":null,"funder_award_id":"AB 675/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1590102137","https://openalex.org/W2114708606","https://openalex.org/W2154649495","https://openalex.org/W2191779130","https://openalex.org/W2261407818","https://openalex.org/W2410860376","https://openalex.org/W2526050071","https://openalex.org/W2763971240","https://openalex.org/W2778340325","https://openalex.org/W2885570506","https://openalex.org/W2899260162","https://openalex.org/W2902583091","https://openalex.org/W2940841377","https://openalex.org/W2990875942","https://openalex.org/W2997076748","https://openalex.org/W3004440566","https://openalex.org/W3015201698","https://openalex.org/W3015591047","https://openalex.org/W3098670224","https://openalex.org/W4288284459","https://openalex.org/W4312805589","https://openalex.org/W6631190155","https://openalex.org/W6635274319","https://openalex.org/W6682548097","https://openalex.org/W6692946518","https://openalex.org/W6745117180","https://openalex.org/W6747336215","https://openalex.org/W6753544557","https://openalex.org/W6756339404","https://openalex.org/W6765921464","https://openalex.org/W6770557639","https://openalex.org/W6891901120"],"related_works":["https://openalex.org/W2494884022","https://openalex.org/W1963961813","https://openalex.org/W600619470","https://openalex.org/W2747010499","https://openalex.org/W2895105879","https://openalex.org/W2133529351","https://openalex.org/W3177981311","https://openalex.org/W598554325","https://openalex.org/W2956875084","https://openalex.org/W2005453118"],"abstract_inverted_index":{"Musicological":[0],"studies":[1,28],"on":[2,84],"jazz":[3,33,58,91],"performance":[4,106],"analysis":[5,39,67],"commonly":[6],"require":[7],"a":[8,65,81,94,115],"manual":[9],"selection":[10],"and":[11,118],"transcription":[12],"of":[13,18,32,53,96,107,148],"improvised":[14,72],"solo":[15,73],"parts,":[16],"both":[17],"which":[19],"can":[20,40,63],"be":[21],"time-consuming.":[22],"In":[23,44],"order":[24,69],"to":[25,29,49,70],"expand":[26],"these":[27,42],"larger":[30],"corpora":[31],"recordings,":[34],"algorithms":[35],"for":[36],"automatic":[37,86],"content":[38],"accelerate":[41],"processes.":[43],"this":[45],"study,":[46],"we":[47,79],"aim":[48],"detect":[50,71],"the":[51,76,105,134,138,152],"presence":[52],"predominant":[54,85],"music":[55],"instruments":[56,99],"in":[57,68,90],"ensemble":[59],"recordings.":[60],"This":[61],"information":[62],"guide":[64],"structural":[66],"parts.":[74],"As":[75],"main":[77,125],"contribution,":[78],"perform":[80,132],"comparative":[82],"study":[83],"instrument":[87],"recognition":[88],"(AIR)":[89],"ensembles":[92],"using":[93],"taxonomy":[95],"11":[97],"common":[98],"including":[100,114],"singing":[101],"voice.":[102],"We":[103],"compare":[104],"three":[108],"state-of-the-art":[109],"convolutional":[110],"neural":[111],"networks":[112,131],"(CNNs)":[113],"recurrent":[116],"variant":[117],"one":[119],"with":[120],"an":[121],"attention":[122],"mechanism.":[123],"Our":[124],"finding":[126],"is":[127,145],"that":[128],"while":[129],"all":[130],"comparably,":[133],"attention-based":[135],"model":[136],"learns":[137],"most":[139],"compact":[140],"feature":[141],"representation":[142],"as":[143],"it":[144],"by":[146],"orders":[147],"magnitude":[149],"smaller":[150],"than":[151],"other":[153],"models.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
