{"id":"https://openalex.org/W4375868847","doi":"https://doi.org/10.1109/icassp49357.2023.10097162","title":"Show Me the Instruments: Musical Instrument Retrieval From Mixture Audio","display_name":"Show Me the Instruments: Musical Instrument Retrieval From Mixture Audio","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868847","doi":"https://doi.org/10.1109/icassp49357.2023.10097162"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5000349069","display_name":"Kyungsu Kim","orcid":"https://orcid.org/0000-0001-6622-6545"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungsu Kim","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information","Department of Intelligence and Information, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101408067","display_name":"Minju Park","orcid":"https://orcid.org/0000-0002-2588-2674"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minju Park","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information","Department of Intelligence and Information, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000309861","display_name":"Haesun Joung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Haesun Joung","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information","Department of Intelligence and Information, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013284291","display_name":"Yunkee Chae","orcid":"https://orcid.org/0009-0000-8073-3754"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunkee Chae","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in Artificial Intelligence","Interdisciplinary Program in Artificial Intelligence, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in Artificial Intelligence","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026263948","display_name":"Yeongbeom Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeongbeom Hong","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information","Department of Intelligence and Information, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008674254","display_name":"Seonghyeon Go","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seonghyeon Go","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information","Department of Intelligence and Information, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Seoul National University,Department of Intelligence and Information","Artificial Intelligence Institute, Seoul National University","Department of Intelligence and Information, Seoul National University","Interdisciplinary Program in Artificial Intelligence, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Artificial Intelligence Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9987999796867371,"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":0.8047335743904114},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7353460788726807},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.6862632632255554},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5282624959945679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45482638478279114},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43694978952407837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3799769878387451},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.19906368851661682},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09263670444488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047335743904114},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7353460788726807},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.6862632632255554},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5282624959945679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45482638478279114},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43694978952407837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799769878387451},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.19906368851661682},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09263670444488525},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1590102137","https://openalex.org/W2187089797","https://openalex.org/W2222512263","https://openalex.org/W2261407818","https://openalex.org/W2296724634","https://openalex.org/W2296752055","https://openalex.org/W2402047267","https://openalex.org/W2410860376","https://openalex.org/W2460742184","https://openalex.org/W2475687244","https://openalex.org/W2533610151","https://openalex.org/W2606176153","https://openalex.org/W2903137797","https://openalex.org/W2963929309","https://openalex.org/W2990912900","https://openalex.org/W2998490864","https://openalex.org/W3034942609","https://openalex.org/W3047059250","https://openalex.org/W3098670224","https://openalex.org/W3160793127","https://openalex.org/W3161301744","https://openalex.org/W3197823486","https://openalex.org/W4205137627","https://openalex.org/W4283360488","https://openalex.org/W4287077834","https://openalex.org/W4298310324","https://openalex.org/W4312443924","https://openalex.org/W6635274319","https://openalex.org/W6692946518","https://openalex.org/W6697040288","https://openalex.org/W6712692208","https://openalex.org/W6736723571","https://openalex.org/W6756597712","https://openalex.org/W6766320909","https://openalex.org/W6781533946","https://openalex.org/W6794356692","https://openalex.org/W6795182721","https://openalex.org/W6798064515","https://openalex.org/W6839196917"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4390516098","https://openalex.org/W2037549926","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2142795561","https://openalex.org/W2849310602","https://openalex.org/W2354332708"],"abstract_inverted_index":{"As":[0],"digital":[1],"music":[2,37],"production":[3],"has":[4],"become":[5],"mainstream,":[6],"the":[7,19,25,89,93,109,123,137,142,170,177,180,187,192,202,207,215],"selection":[8],"of":[9,21,88,148,183],"appropriate":[10],"virtual":[11,30],"instruments":[12,31,76,110,185,209],"plays":[13],"a":[14,70,82,146,161],"crucial":[15],"role":[16],"in":[17,49,112],"determining":[18],"quality":[20],"music.":[22],"To":[23],"search":[24],"musical":[26,75],"instrument":[27,47,124,134,138,188],"samples":[28,219],"or":[29],"that":[32,169],"make":[33],"one\u2019s":[34],"desired":[35,74,208],"sound,":[36],"producers":[38],"use":[39],"their":[40,50],"ears":[41],"to":[42,107,131,175,186,197],"listen":[43],"and":[44,55,68,92,115,155,191,205,217],"compare":[45],"each":[46],"sample":[48],"collection,":[51],"which":[52],"is":[53,105,129],"time-consuming":[54],"inefficient.":[56],"In":[57],"this":[58,62],"paper,":[59],"we":[60,116,158],"call":[61],"task":[63],"as":[64,81,122,145],"Musical":[65],"Instrument":[66],"Retrieval":[67],"propose":[69,160],"method":[71],"for":[72,214],"retrieving":[73],"using":[77,136],"reference":[78],"mixture":[79,203],"audio":[80,181,204,218],"query.":[83],"The":[84,102,126,211],"proposed":[85],"model":[86],"consists":[87],"Single-Instrument":[90,103,143,171],"Encoder":[91,104,128,144,172,194],"Multi-Instrument":[94,127,193],"Encoder,":[95],"both":[96],"based":[97],"on":[98],"convolutional":[99],"neural":[100],"networks.":[101],"trained":[106,130],"classify":[108],"used":[111,213],"single-track":[113],"audio,":[114],"take":[117],"its":[118],"penultimate":[119],"layer\u2019s":[120],"activation":[121],"embedding.":[125],"estimate":[132],"multiple":[133,199],"embeddings":[135,139,200],"computed":[140],"by":[141],"set":[147],"target":[149],"embeddings.":[150],"For":[151],"more":[152],"generalized":[153],"training":[154],"realistic":[156],"evaluation,":[157],"also":[159],"new":[162],"dataset":[163],"called":[164],"Nlakh.":[165],"Experimental":[166],"results":[167],"showed":[168],"was":[173,195],"able":[174,196],"learn":[176],"mapping":[178],"from":[179,201],"signal":[182],"unseen":[184],"embedding":[189],"space":[190],"extract":[198],"retrieve":[206],"successfully.":[210],"code":[212],"experiment":[216],"are":[220],"available":[221],"at:":[222],"https://github.com/minju0821/musical_instrument_retrieval":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}