{"id":"https://openalex.org/W6967456180","doi":"https://doi.org/10.5281/zenodo.10265215","title":"TriAD: Capturing Harmonics With 3D Convolutions","display_name":"TriAD: Capturing Harmonics With 3D Convolutions","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6967456180","doi":"https://doi.org/10.5281/zenodo.10265215"},"language":"en","primary_location":{"id":"pmh:oai:repositori-api.upf.edu:10230/58109","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/58109","pdf_url":"https://repositori.upf.edu/bitstreams/d1e7ef52-c562-45df-86a5-383227e0d028/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/submittedVersion"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/d1e7ef52-c562-45df-86a5-383227e0d028/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Miguel Perez","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Miguel Perez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Holger Kirchhoff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Holger Kirchhoff","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1971,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5188049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8317999839782715,"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":0.8317999839782715,"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":0.07930000126361847,"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":0.03590000048279762,"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/harmonics","display_name":"Harmonics","score":0.6209999918937683},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5449000000953674},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.49149999022483826},{"id":"https://openalex.org/keywords/dilation","display_name":"Dilation (metric space)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.4374000132083893},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4293999969959259},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4223000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6463000178337097},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.6209999918937683},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C2780757906","wikidata":"https://www.wikidata.org/wiki/Q5276676","display_name":"Dilation (metric space)","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.38920000195503235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:repositori-api.upf.edu:10230/58109","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/58109","pdf_url":"https://repositori.upf.edu/bitstreams/d1e7ef52-c562-45df-86a5-383227e0d028/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/submittedVersion"},{"id":"doi:10.5281/zenodo.10265215","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265215","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"pmh:oai:repositori-api.upf.edu:10230/58109","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/58109","pdf_url":"https://repositori.upf.edu/bitstreams/d1e7ef52-c562-45df-86a5-383227e0d028/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/submittedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6967456180.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Thanks":[0],"to":[1,60,79,104],"advancements":[2],"in":[3,49],"deep":[4],"learning":[5],"(DL),":[6],"automatic":[7],"music":[8],"transcription":[9],"(AMT)":[10],"systems":[11],"recently":[12],"outperformed":[13],"previous":[14],"ones":[15],"fully":[16],"based":[17],"on":[18,152],"manual":[19],"feature":[20],"design.":[21],"Many":[22],"of":[23,40,120,136],"these":[24],"highly":[25],"capable":[26,39],"DL":[27],"models,":[28],"however,":[29,67],"are":[30,34],"computationally":[31],"expensive.":[32],"Researchers":[33],"moving":[35],"towards":[36],"smaller":[37],"models":[38],"maintaining":[41],"state-of-the-art":[42],"(SOTA)":[43],"results":[44,131],"by":[45],"embedding":[46],"musical":[47],"knowledge":[48],"the":[50,62,97,134],"network":[51],"architecture.":[52],"Existing":[53],"approaches":[54],"employ":[55],"convolutional":[56,88],"blocks":[57],"specifically":[58],"designed":[59],"capture":[61,80,105],"harmonic":[63,153],"structure.":[64],"These":[65],"approaches,":[66],"require":[68],"either":[69],"large":[70],"kernels":[71],"or":[72],"multiple":[73,106],"kernels,":[74],"with":[75,108,117],"each":[76],"kernel":[77],"aiming":[78],"a":[81,87,109],"different":[82],"harmonic.":[83],"We":[84,114,139],"present":[85],"TriAD,":[86],"block":[89],"that":[90,126,146],"achieves":[91],"an":[92,142],"unequally":[93],"distanced":[94],"dilation":[95],"over":[96],"frequency":[98],"axis.":[99],"This":[100],"allows":[101],"our":[102,127,147],"method":[103,149],"harmonics":[107],"single":[110],"yet":[111],"small":[112],"kernel.":[113],"compare":[115],"TriAD":[116],"other":[118],"methods":[119],"capturing":[121],"harmonics,":[122],"and":[123],"we":[124],"observe":[125],"approach":[128],"maintains":[129],"SOTA":[130],"while":[132],"reducing":[133],"number":[135],"parameters":[137],"required.":[138],"also":[140],"conduct":[141],"ablation":[143],"study":[144],"showing":[145],"proposed":[148],"effectively":[150],"relies":[151],"information.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}