{"id":"https://openalex.org/W4390604258","doi":"https://doi.org/10.1109/taslp.2023.3349053","title":"Audio Super-Resolution With Robust Speech Representation Learning of Masked Autoencoder","display_name":"Audio Super-Resolution With Robust Speech Representation Learning of Masked Autoencoder","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390604258","doi":"https://doi.org/10.1109/taslp.2023.3349053"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3349053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3349053","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10381805.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10381805.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007493723","display_name":"Seung-Bin Kim","orcid":"https://orcid.org/0000-0002-2287-9111"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033958396","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-8925-4474"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102753650","display_name":"Ha-Yeong Choi","orcid":"https://orcid.org/0000-0003-2390-7628"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Yeong Choi","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2010Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007493723"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":6.4894,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97377067,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"1012","last_page":"1022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9905999898910522,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9828000068664551,"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":0.7799060344696045},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7086321115493774},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6519651412963867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6351733803749084},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5964948534965515},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5872467756271362},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5405252575874329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5090388655662537},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43829795718193054},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41187506914138794},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.324849009513855},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2591007351875305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7799060344696045},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7086321115493774},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6519651412963867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6351733803749084},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5964948534965515},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5872467756271362},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5405252575874329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5090388655662537},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43829795718193054},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41187506914138794},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.324849009513855},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2591007351875305},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3349053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3349053","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10381805.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3349053","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3349053","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10381805.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1478288009","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2953128317","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G398188885","display_name":null,"funder_award_id":"2019-0-0007","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4643994530","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7640390086","display_name":null,"funder_award_id":"019-0-00079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G8176700800","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8241800567","display_name":null,"funder_award_id":"2021-0-0206","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8436554242","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390604258.pdf","grobid_xml":"https://content.openalex.org/works/W4390604258.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1635564296","https://openalex.org/W1901129140","https://openalex.org/W2052791563","https://openalex.org/W2100285470","https://openalex.org/W2171815504","https://openalex.org/W2289169846","https://openalex.org/W2399742709","https://openalex.org/W2519091744","https://openalex.org/W2784918340","https://openalex.org/W2802034954","https://openalex.org/W2892335023","https://openalex.org/W2924508610","https://openalex.org/W2940120659","https://openalex.org/W2972359262","https://openalex.org/W2972894903","https://openalex.org/W2973042454","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3037038648","https://openalex.org/W3093990297","https://openalex.org/W3095095816","https://openalex.org/W3095802501","https://openalex.org/W3109064156","https://openalex.org/W3122318757","https://openalex.org/W3125868443","https://openalex.org/W3138516171","https://openalex.org/W3160652646","https://openalex.org/W3163243746","https://openalex.org/W3173081491","https://openalex.org/W3174285493","https://openalex.org/W3180374548","https://openalex.org/W3196468212","https://openalex.org/W3197273793","https://openalex.org/W3197334236","https://openalex.org/W3197990672","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211264909","https://openalex.org/W4220739185","https://openalex.org/W4221155904","https://openalex.org/W4224133928","https://openalex.org/W4224920322","https://openalex.org/W4281736089","https://openalex.org/W4283215837","https://openalex.org/W4285412734","https://openalex.org/W4297841853","https://openalex.org/W4307323391","https://openalex.org/W4313156423","https://openalex.org/W4372260387","https://openalex.org/W4375869358","https://openalex.org/W4376456759","https://openalex.org/W4381786045","https://openalex.org/W4385823183","https://openalex.org/W4392903177","https://openalex.org/W6741681139","https://openalex.org/W6748409065","https://openalex.org/W6757817989","https://openalex.org/W6760993068","https://openalex.org/W6767111847","https://openalex.org/W6767367760","https://openalex.org/W6772349387","https://openalex.org/W6777694618","https://openalex.org/W6779337556","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6784333009","https://openalex.org/W6784457260","https://openalex.org/W6786325012","https://openalex.org/W6840200333","https://openalex.org/W6843673214","https://openalex.org/W6856205631"],"related_works":["https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3174572320","https://openalex.org/W4287115985","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"Fre-Painter,":[3],"a":[4,81,104],"high-fidelity":[5],"audio":[6,33,52,76,124],"super-resolution":[7,125],"system":[8],"that":[9,85,119],"utilizes":[10],"robust":[11,30,89],"speech":[12,35,92,110,113],"representation":[13],"learning":[14,29],"with":[15,63,93],"various":[16,94],"masking":[17,48,61,83],"strategies.":[18],"Recently,":[19],"masked":[20],"autoencoders":[21],"have":[22],"been":[23],"found":[24],"to":[25,103],"be":[26],"beneficial":[27],"in":[28],"representations":[31,44],"of":[32,66],"for":[34,50,75,90],"classification":[36],"tasks.":[37],"Following":[38],"these":[39,43],"studies,":[40],"we":[41,57,79,100],"leverage":[42],"and":[45],"investigate":[46],"several":[47],"strategies":[49],"neural":[51,123],"super-resolution.":[53,77],"In":[54],"this":[55],"paper,":[56],"propose":[58,80],"an":[59],"upper-band":[60],"strategy":[62,84],"the":[64,67,87],"initialization":[65],"mask":[68],"token,":[69],"which":[70,107],"is":[71],"simple":[72],"but":[73],"efficient":[74],"Furthermore,":[78],"mix-ratio":[82],"makes":[86],"model":[88],"input":[91],"sampling":[95],"rates.":[96],"For":[97],"practical":[98],"applicability,":[99],"extend":[101],"Fre-Painter":[102,120],"text-to-speech":[105],"system,":[106],"synthesizes":[108],"high-resolution":[109],"using":[111],"low-resolution":[112],"data.":[114],"The":[115],"experimental":[116],"results":[117],"demonstrate":[118],"outperforms":[121],"other":[122],"models.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
