{"id":"https://openalex.org/W4296103737","doi":"https://doi.org/10.5281/zenodo.4285396","title":"Extending Deep Rhythm for Tempo and Genre Estimation Using Complex Convolutions, Multitask Learning and Multi-input Network","display_name":"Extending Deep Rhythm for Tempo and Genre Estimation Using Complex Convolutions, Multitask Learning and Multi-input Network","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W4296103737","doi":"https://doi.org/10.5281/zenodo.4285396"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.4285396","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285396","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.4285396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Foroughm, Hadrien","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Foroughm, Hadrien","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peeters, Geoffroy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26410273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9787999987602234,"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":0.9787999987602234,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.007199999876320362,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.004399999976158142,"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":0.7668470144271851},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.7392027378082275},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5340978503227234},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5304821133613586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5162134766578674},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4799799621105194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36805427074432373},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3276893198490143},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.22818368673324585},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06431639194488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668470144271851},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.7392027378082275},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5340978503227234},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5304821133613586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5162134766578674},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4799799621105194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36805427074432373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3276893198490143},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.22818368673324585},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06431639194488525},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.4285396","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285396","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.4285396","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285396","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2989698750","https://openalex.org/W2597787948","https://openalex.org/W2951786554","https://openalex.org/W4223943233","https://openalex.org/W3031818154","https://openalex.org/W3181335979","https://openalex.org/W3047894882","https://openalex.org/W3208584567","https://openalex.org/W4221031031"],"abstract_inverted_index":{"Tempo":[0],"and":[1,109],"genre":[2,110],"are":[3,10,17],"two":[4],"inter-leaved":[5],"aspects":[6],"of":[7,39,69,81],"music,":[8],"genres":[9],"often":[11],"associated":[12],"to":[13,45,86,95,103],"rhythm":[14,40],"patterns":[15],"which":[16],"played":[18],"in":[19],"specific":[20],"tempo":[21,108],"ranges.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,57,77],"focus":[27],"on":[28,35,90],"the":[29,52,66,79,87,105],"recent":[30],"Deep":[31],"Rhythm":[32],"system":[33,88],"based":[34,89],"a":[36,46,72,82,91,96],"harmonic":[37],"representation":[38],"used":[41],"as":[42],"an":[43],"input":[44,84],"convolutional":[47],"neural":[48],"network.":[49],"To":[50],"consider":[51],"relationships":[53],"between":[54],"frequency":[55],"bands,":[56],"process":[58],"complex-valued":[59],"inputs":[60],"through":[61],"complexconvolutions.":[62],"We":[63],"also":[64],"study":[65,78],"joint":[67],"estimation":[68],"tempo/genre":[70],"using":[71],"multitask":[73],"learning":[74],"approach.":[75],"Finally,":[76],"addition":[80],"second":[83],"branch":[85],"VGG-like":[92],"architecture":[93],"applied":[94],"mel-spectrogram":[97],"input.":[98],"This":[99],"multi-input":[100],"approach":[101],"allows":[102],"improve":[104],"performances":[106],"for":[107],"estimation.":[111]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2025-10-10T00:00:00"}