{"id":"https://openalex.org/W4392909364","doi":"https://doi.org/10.1109/icassp48485.2024.10447318","title":"Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training","display_name":"Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909364","doi":"https://doi.org/10.1109/icassp48485.2024.10447318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447318","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":"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","Interdisciplinary Program in Artificial Intelligence, Seoul National University","Department of Intelligence and Information, Seoul National University","Artificial Intelligence Institute, 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":"Interdisciplinary Program in Artificial Intelligence, 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":"Artificial Intelligence Institute, 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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"526","last_page":"530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9578999876976013,"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/adversarial-system","display_name":"Adversarial system","score":0.8126457333564758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194074988365173},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6690654754638672},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5714746713638306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456893444061279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5211398601531982},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5057075023651123},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4999873638153076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09587833285331726}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8126457333564758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194074988365173},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6690654754638672},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5714746713638306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456893444061279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5211398601531982},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5057075023651123},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4999873638153076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09587833285331726},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447318","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320323890","display_name":"Korea Creative Content Agency","ror":"https://ror.org/036vyg793"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1577269164","https://openalex.org/W1731081199","https://openalex.org/W2219249508","https://openalex.org/W2414894569","https://openalex.org/W2592168896","https://openalex.org/W2593116425","https://openalex.org/W2767858146","https://openalex.org/W2794150026","https://openalex.org/W2952395326","https://openalex.org/W2963451564","https://openalex.org/W2964218314","https://openalex.org/W3105202226","https://openalex.org/W3139211892","https://openalex.org/W4286850225","https://openalex.org/W4296068785","https://openalex.org/W4304699761","https://openalex.org/W4381710926","https://openalex.org/W4385245566","https://openalex.org/W4385374136","https://openalex.org/W4388473442","https://openalex.org/W6631190155","https://openalex.org/W6634441602","https://openalex.org/W6637618735","https://openalex.org/W6678969435","https://openalex.org/W6688816777","https://openalex.org/W6715395060","https://openalex.org/W6745878906","https://openalex.org/W6763945542","https://openalex.org/W6764574124","https://openalex.org/W6774314701","https://openalex.org/W6791537541","https://openalex.org/W6803752119","https://openalex.org/W6846470732","https://openalex.org/W6852985890","https://openalex.org/W6855682633"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4394050964","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Music":[0,13],"auto-tagging":[1,42,109],"is":[2],"crucial":[3],"for":[4,75],"enhancing":[5],"music":[6,41,56,60,91,108,115],"discovery":[7],"and":[8,24,133],"recommendation.":[9],"Existing":[10],"models":[11],"in":[12,27,44,83,107],"Information":[14],"Retrieval":[15],"(MIR)":[16],"struggle":[17],"with":[18,119],"real-world":[19],"noise":[20,99],"such":[21],"as":[22],"environmental":[23],"speech":[25],"sounds":[26],"multimedia":[28],"content.":[29],"This":[30],"study":[31],"proposes":[32],"a":[33],"method":[34],"inspired":[35],"by":[36,110],"speech-related":[37],"tasks":[38],"to":[39,79],"enhance":[40],"performance":[43,81,106],"noisy":[45,90,114],"settings.":[46],"The":[47,101],"approach":[48,69],"integrates":[49],"Domain":[50],"Adversarial":[51],"Training":[52],"(DAT)":[53],"into":[54],"the":[55,76,84,94,125],"domain,":[57],"enabling":[58],"robust":[59,130],"representations":[61],"that":[62],"withstand":[63],"noise.":[64],"Unlike":[65],"previous":[66],"research,":[67],"this":[68],"involves":[70],"an":[71],"additional":[72],"pretraining":[73],"phase":[74],"domain":[77],"classifier,":[78],"avoid":[80],"degradation":[82],"subsequent":[85],"phase.":[86],"Adding":[87],"various":[88],"synthesized":[89],"data":[92,122],"improves":[93,124],"model\u2019s":[95,126],"generalization":[96,131],"across":[97],"different":[98],"levels.":[100],"proposed":[102],"architecture":[103],"demonstrates":[104],"enhanced":[105],"effectively":[111],"utilizing":[112],"unlabeled":[113,121],"data.":[116],"Additional":[117],"experiments":[118],"supplementary":[120],"further":[123],"performance,":[127],"underscoring":[128],"its":[129],"capabilities":[132],"broad":[134],"applicability.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}