{"id":"https://openalex.org/W4387968182","doi":"https://doi.org/10.1145/3581783.3612269","title":"Exploiting Time-Frequency Conformers for Music Audio Enhancement","display_name":"Exploiting Time-Frequency Conformers for Music Audio Enhancement","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968182","doi":"https://doi.org/10.1145/3581783.3612269"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/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, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-8073-3754","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"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":"Junghyun Koo","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-4468-0367","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402786","display_name":"Sungho Lee","orcid":"https://orcid.org/0000-0002-7421-9529"},"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":"Sungho Lee","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7421-9529","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","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, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4210-0312","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","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":null,"issue":null,"first_page":"2362","last_page":"2370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7098249793052673},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5305522084236145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5196455717086792},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46318933367729187},{"id":"https://openalex.org/keywords/performance-enhancement","display_name":"Performance enhancement","score":0.4555768072605133},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4451448619365692},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.42169299721717834},{"id":"https://openalex.org/keywords/dynamic-range-compression","display_name":"Dynamic range compression","score":0.4121939241886139},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3420332968235016},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.33432474732398987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19865167140960693},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1352982223033905},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0920133888721466},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07675468921661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098249793052673},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5305522084236145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5196455717086792},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46318933367729187},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.4555768072605133},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4451448619365692},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.42169299721717834},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.4121939241886139},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3420332968235016},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.33432474732398987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19865167140960693},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1352982223033905},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0920133888721466},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07675468921661377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612269","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":23,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2144404214","https://openalex.org/W2172491908","https://openalex.org/W2476548250","https://openalex.org/W2593414223","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963992487","https://openalex.org/W2964070952","https://openalex.org/W2972411915","https://openalex.org/W3015197852","https://openalex.org/W3015338123","https://openalex.org/W3037149862","https://openalex.org/W3092028330","https://openalex.org/W3096408984","https://openalex.org/W3162501355","https://openalex.org/W3177067699","https://openalex.org/W3197729725","https://openalex.org/W3211197703","https://openalex.org/W4224932134","https://openalex.org/W4224932531","https://openalex.org/W4224934178","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W2124672476","https://openalex.org/W1535381740","https://openalex.org/W2105867363","https://openalex.org/W3168109306","https://openalex.org/W2135485548","https://openalex.org/W2373767407","https://openalex.org/W2187949121","https://openalex.org/W2143698818","https://openalex.org/W2376606440","https://openalex.org/W2251439150"],"abstract_inverted_index":{"With":[0],"the":[1,7,33,37,53,67,82,97,101,109,113],"proliferation":[2],"of":[3,55,100],"video":[4],"platforms":[5],"on":[6,81,128],"internet,":[8],"recording":[9],"musical":[10],"performances":[11],"by":[12],"mobile":[13],"devices":[14],"has":[15,63,86,144],"become":[16],"commonplace.":[17],"However,":[18],"these":[19],"recordings":[20,58],"often":[21],"suffer":[22],"from":[23,48],"degradation":[24],"such":[25],"as":[26,45],"noise":[27],"and":[28,103],"reverberation,":[29],"which":[30,143],"negatively":[31],"impact":[32],"listening":[34],"experience.":[35,69],"Consequently,":[36],"necessity":[38],"for":[39,112],"music":[40,46,77,114,130,138],"audio":[41,57],"enhancement":[42,47,78,92,115,139],"(referred":[43],"to":[44,65,107],"this":[49,72],"point":[50],"onward),":[51],"involving":[52],"transformation":[54],"degraded":[56],"into":[59],"pristine":[60],"high-quality":[61],"music,":[62],"surged":[64],"augment":[66],"auditory":[68],"To":[70],"address":[71],"issue,":[73],"we":[74],"propose":[75],"a":[76],"system":[79,134,156],"based":[80],"Conformer":[83,102],"architecture":[84],"that":[85,121],"demonstrated":[87],"outstanding":[88],"performance":[89,106,127],"in":[90,148],"speech":[91],"tasks.":[93],"Our":[94,117],"approach":[95,111],"explores":[96],"attention":[98],"mechanisms":[99],"examines":[104],"their":[105],"discover":[108],"best":[110],"task.":[116],"experimental":[118],"results":[119],"show":[120],"our":[122,133,155],"proposed":[123],"model":[124],"achieves":[125],"state-of-the-art":[126],"single-stem":[129],"enhancement.":[131],"Furthermore,":[132],"can":[135],"perform":[136],"general":[137],"with":[140,154],"multi-track":[141],"mixtures,":[142],"not":[145],"been":[146],"examined":[147],"previous":[149],"work.":[150],"Audio":[151],"samples":[152],"enhanced":[153],"are":[157],"available":[158],"at:":[159],"https://tinyurl.com/smpls9999":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
