{"id":"https://openalex.org/W2583165630","doi":"https://doi.org/10.1109/icassp.2017.7952601","title":"Designing efficient architectures for modeling temporal features with convolutional neural networks","display_name":"Designing efficient architectures for modeling temporal features with convolutional neural networks","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2583165630","doi":"https://doi.org/10.1109/icassp.2017.7952601","mag":"2583165630"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":7.3402,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97952672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2472","last_page":"2476"},"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":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.80796217918396},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6290536522865295},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5615707635879517},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5572917461395264},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5371331572532654},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5250037908554077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4649554491043091},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4590666592121124},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.45562314987182617},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4539416432380676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34359508752822876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33258068561553955},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20755299925804138},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.15921151638031006},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10090482234954834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80796217918396},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6290536522865295},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5615707635879517},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5572917461395264},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5371331572532654},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5250037908554077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4649554491043091},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4590666592121124},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.45562314987182617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4539416432380676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34359508752822876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33258068561553955},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20755299925804138},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.15921151638031006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10090482234954834},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7952601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/33811","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/33811","pdf_url":null,"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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1721549435","https://openalex.org/W2042390666","https://openalex.org/W2059652044","https://openalex.org/W2294252515","https://openalex.org/W2395731347","https://openalex.org/W2402347808","https://openalex.org/W2414894569","https://openalex.org/W2437181147","https://openalex.org/W2963158330","https://openalex.org/W2963369619","https://openalex.org/W3098670224","https://openalex.org/W6697413020","https://openalex.org/W6715395060"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Many":[0],"researchers":[1],"use":[2,23],"convolutional":[3],"neural":[4],"networks":[5],"with":[6,118],"small":[7],"rectangular":[8],"filters":[9,25],"for":[10],"music":[11,45],"(spectrograms)":[12],"classification.":[13],"First,":[14],"we":[15,31,54],"discuss":[16],"why":[17],"there":[18],"is":[19,125],"no":[20],"reason":[21],"to":[22,86],"this":[24,123],"setup":[26],"by":[27,70,99],"default":[28],"and":[29,65],"second,":[30],"point":[32],"that":[33,60,122],"more":[34,63],"efficient":[35],"architectures":[36,69,96],"could":[37],"be":[38],"implemented":[39],"if":[40],"the":[41,44,50,73,77,91,105,108,119],"characteristics":[42],"of":[43,76,107],"features":[46],"are":[47,97],"considered":[48],"during":[49],"design":[51,58],"process.":[52],"Specifically,":[53],"propose":[55],"a":[56],"novel":[57],"strategy":[59],"might":[61],"promote":[62],"expressive":[64],"intuitive":[66],"deep":[67],"learning":[68],"efficiently":[71],"exploiting":[72],"representational":[74],"capacity":[75],"first":[78,92],"layer":[79],"-":[80],"using":[81],"different":[82],"filter":[83],"shapes":[84],"adapted":[85],"fit":[87],"musical":[88],"concepts":[89],"within":[90],"layer.":[93],"The":[94],"proposed":[95],"assessed":[98],"measuring":[100],"their":[101],"accuracy":[102],"in":[103],"predicting":[104],"classes":[106],"Ballroom":[109],"dataset.":[110],"We":[111],"also":[112],"make":[113],"available1the":[114],"used":[115],"code":[116],"(together":[117],"audio-data)":[120],"so":[121],"research":[124],"fully":[126],"reproducible.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}