{"id":"https://openalex.org/W4406495765","doi":"https://doi.org/10.1109/bigdata62323.2024.10825438","title":"Decomposing Audio into Timbral Features with Convolutional Neural Networks","display_name":"Decomposing Audio into Timbral Features with Convolutional Neural Networks","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406495765","doi":"https://doi.org/10.1109/bigdata62323.2024.10825438"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5093413139","display_name":"Nicole Cosme-Clifford","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicole Cosme-Clifford","raw_affiliation_strings":["Yale University,New Haven,CT,USA"],"affiliations":[{"raw_affiliation_string":"Yale University,New Haven,CT,USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5093413139"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29405151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3168","last_page":"3173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9947999715805054,"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":0.7891349792480469},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7626138925552368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5624661445617676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3728458881378174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891349792480469},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7626138925552368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5624661445617676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3728458881378174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2059652044","https://openalex.org/W2559688696","https://openalex.org/W2580221632","https://openalex.org/W2767858146","https://openalex.org/W2794150026","https://openalex.org/W2963232038","https://openalex.org/W2964218314","https://openalex.org/W3023104975","https://openalex.org/W4206782543","https://openalex.org/W4206995848","https://openalex.org/W4287802874","https://openalex.org/W4318351475","https://openalex.org/W4380136719","https://openalex.org/W4391586430","https://openalex.org/W6730401039","https://openalex.org/W6732646663","https://openalex.org/W6745878906","https://openalex.org/W6776218486","https://openalex.org/W6849105126","https://openalex.org/W6853096648"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"AI":[0],"has":[1],"gained":[2],"traction":[3],"in":[4,8,20],"industry":[5],"and":[6,11,150,163,218],"academia":[7],"recent":[9],"years,":[10],"music":[12,40,44,82],"is":[13,22,102,129],"no":[14],"exception.":[15],"Part":[16],"of":[17,39,112,136,204,213,222],"this":[18,182,187],"increase":[19],"visibility":[21],"due":[23],"to":[24,74,98,159,179],"new":[25,220],"methods":[26,47],"that":[27,125,167],"process":[28],"audio":[29,72,196],"recordings":[30,73],"directly,":[31],"rather":[32],"than":[33],"relying":[34],"solely":[35],"on":[36,95],"symbolic":[37],"representations":[38],"like":[41,81,171],"spectrograms":[42],"or":[43,84],"notation.":[45],"These":[46],"commonly":[48],"use":[49],"one-dimensional":[50],"(1D)":[51],"filter":[52,88,115,127,190],"convolution,":[53,116],"a":[54,205],"well-established":[55],"signal":[56,226],"processing":[57],"technique":[58],"built":[59],"into":[60],"deep":[61],"neural":[62,216],"networks.":[63],"In":[64],"musical":[65,100,138],"AI,":[66],"1D":[67,87,114,126,189,214,225],"convolutional":[68,215],"filters":[69],"analyze":[70],"digital":[71],"extract":[75],"sonic":[76],"features":[77,101,134],"useful":[78],"for":[79],"tasks":[80],"generation":[83],"recommendation.":[85],"Despite":[86],"convolution\u2019s":[89],"increasing":[90],"prevalence,":[91],"though,":[92],"its":[93],"impact":[94],"AI\u2019s":[96],"ability":[97,178],"learn":[99],"underexplored.This":[103],"paper":[104],"addresses":[105],"these":[106],"gaps":[107],"through":[108],"an":[109],"epistemic":[110],"study":[111,183],"AI-based":[113],"offering":[117],"two":[118],"novel":[119],"contributions.":[120],"First,":[121],"experimental":[122],"results":[123],"show":[124],"convolution":[128,191],"heavily":[130],"biased.":[131],"It":[132],"favors":[133],"typical":[135],"synthetic":[137],"styles,":[139],"such":[140],"as":[141,201],"electronic":[142],"dance":[143],"music,":[144,173],"where":[145],"sounds":[146,166],"are":[147],"highly":[148],"repetitive":[149],"often":[151],"have":[152],"simple":[153],"frequency":[154],"spectra.":[155],"However,":[156],"it":[157],"struggles":[158],"capture":[160],"the":[161,176,202,210],"inconsistent":[162],"spectrally":[164],"complex":[165],"characterize":[168],"acoustic":[169],"styles":[170],"folk":[172],"thereby":[174],"constraining":[175],"network\u2019s":[177],"generalize.":[180],"Second,":[181],"shows":[184],"that,":[185],"despite":[186],"bias,":[188],"can":[192],"effectively":[193],"parse":[194],"large":[195],"collections":[197],"by":[198],"timbre\u2013\u2013broadly":[199],"defined":[200],"quality":[203],"sound.":[206],"This":[207],"finding":[208],"expands":[209],"potential":[211],"applications":[212],"networks":[217],"suggests":[219],"ways":[221],"working":[223],"with":[224],"data.":[227]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}