{"id":"https://openalex.org/W3133859501","doi":"https://doi.org/10.1109/icassp39728.2021.9414038","title":"Reverb Conversion Of Mixed Vocal Tracks Using An End-To-End Convolutional Deep Neural Network","display_name":"Reverb Conversion Of Mixed Vocal Tracks Using An End-To-End Convolutional Deep Neural Network","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3133859501","doi":"https://doi.org/10.1109/icassp39728.2021.9414038","mag":"3133859501"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.02147","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Music and Audio Research Group,Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group,Department of Intelligence and Information","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035078120","display_name":"Seungryeol Paik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seungryeol Paik","raw_affiliation_strings":["Music and Audio Research Group,Department of Intelligence and Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group,Department of Intelligence and Information","institution_ids":[]}]},{"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":["Music and Audio Research Group,Department of Intelligence and Information","Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group,Department of Intelligence and Information","institution_ids":[]},{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1805,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29872998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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/T11008","display_name":"Aerodynamics and Acoustics in Jet Flows","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7516668438911438},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6366437077522278},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.5852242708206177},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5702621340751648},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.5675211548805237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5523381233215332},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43909239768981934},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42324337363243103},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4227650463581085},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41675886511802673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38606521487236023},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.24911978840827942},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23613017797470093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516668438911438},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6366437077522278},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.5852242708206177},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5702621340751648},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.5675211548805237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5523381233215332},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43909239768981934},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42324337363243103},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4227650463581085},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41675886511802673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38606521487236023},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.24911978840827942},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23613017797470093},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.02147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02147","pdf_url":"https://arxiv.org/pdf/2103.02147","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3133859501","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.02147.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.02147","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.02147","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/tcwr-bs23","is_oa":true,"landing_page_url":"https://doi.org/10.17023/tcwr-bs23","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.02147","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.02147","pdf_url":"https://arxiv.org/pdf/2103.02147","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3133859501.pdf","grobid_xml":"https://content.openalex.org/works/W3133859501.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W75187673","https://openalex.org/W1558898279","https://openalex.org/W1710476689","https://openalex.org/W1901129140","https://openalex.org/W1935589317","https://openalex.org/W1989314204","https://openalex.org/W2002507711","https://openalex.org/W2035412504","https://openalex.org/W2067295501","https://openalex.org/W2164502538","https://openalex.org/W2275990807","https://openalex.org/W2542605056","https://openalex.org/W2558661413","https://openalex.org/W2591246382","https://openalex.org/W2752782242","https://openalex.org/W2754165686","https://openalex.org/W2774707525","https://openalex.org/W2906042495","https://openalex.org/W2946947453","https://openalex.org/W2963420686","https://openalex.org/W2964058413","https://openalex.org/W2972162845","https://openalex.org/W2982082915","https://openalex.org/W2994689640","https://openalex.org/W3015354039","https://openalex.org/W3042853995","https://openalex.org/W3095913803","https://openalex.org/W3099468121","https://openalex.org/W6637568146","https://openalex.org/W6639824700","https://openalex.org/W6694752800","https://openalex.org/W6746914816","https://openalex.org/W6757632829","https://openalex.org/W6763039619","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W3163735648","https://openalex.org/W2986673441","https://openalex.org/W2921904817","https://openalex.org/W3008054319","https://openalex.org/W2092574699","https://openalex.org/W3015710813","https://openalex.org/W2083492983","https://openalex.org/W3082087924","https://openalex.org/W2997938083","https://openalex.org/W2186901608","https://openalex.org/W3081378361","https://openalex.org/W2970176078","https://openalex.org/W2929686089","https://openalex.org/W2990594533","https://openalex.org/W3177975252","https://openalex.org/W165802372","https://openalex.org/W58785910","https://openalex.org/W2564948744","https://openalex.org/W2114103002","https://openalex.org/W3187219273"],"abstract_inverted_index":{"Reverb":[0],"plays":[1],"a":[2,31,94],"critical":[3],"role":[4],"in":[5,103],"music":[6,33,155],"production,":[7],"where":[8],"it":[9,22,111],"provides":[10],"listeners":[11],"with":[12,105,131],"spatial":[13],"realization,":[14],"timbre,":[15],"and":[16],"texture":[17],"of":[18,30,47,53,67,135,140,157],"the":[19,27,49,65,68,72,77,88,123,128,132,138,145],"music.":[20],"Yet,":[21],"is":[23,79,91,101,144],"challenging":[24],"to":[25,63,71,75,113,148,153],"reproduce":[26],"musical":[28,50],"reverb":[29,51,66,129,156],"reference":[32,69,89],"track":[34,70,74,90],"even":[35],"by":[36],"skilled":[37],"engineers.":[38],"In":[39],"response,":[40],"we":[41],"propose":[42],"an":[43,106],"end-to-end":[44],"system":[45],"capable":[46],"switching":[48],"factor":[52,130],"two":[54],"different":[55],"mixed":[56],"vocal":[57,96,158],"tracks.":[58,159],"This":[59],"method":[60],"enables":[61],"us":[62],"apply":[64,149],"source":[73],"which":[76,109],"effect":[78],"desired.":[80],"Further,":[81],"our":[82,141],"model":[83,100,125],"can":[84,126],"perform":[85],"de-reverberation":[86],"when":[87],"used":[92],"as":[93],"dry":[95],"source.":[97],"The":[98,118],"proposed":[99,124],"trained":[102],"combination":[104],"adversarial":[107],"objective,":[108],"makes":[110],"possible":[112],"handle":[114],"high-resolution":[115],"audio":[116],"samples.":[117],"perceptual":[119],"evaluation":[120],"confirmed":[121],"that":[122],"convert":[127],"preferred":[133],"rate":[134],"64.8%.":[136],"To":[137],"best":[139],"knowledge,":[142],"this":[143],"first":[146],"attempt":[147],"deep":[150],"neural":[151],"networks":[152],"converting":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}