{"id":"https://openalex.org/W4389943413","doi":"https://doi.org/10.1109/access.2023.3345027","title":"SelfRemaster: Self-Supervised Speech Restoration for Historical Audio Resources","display_name":"SelfRemaster: Self-Supervised Speech Restoration for Historical Audio Resources","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389943413","doi":"https://doi.org/10.1109/access.2023.3345027"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3345027","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3345027","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10366219.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10366219.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6003-768X","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0520-7847","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4385-7170","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059290592","display_name":"Naoko Tanji","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoko Tanji","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0876-5617","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025983709"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.674,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76661431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"144831","last_page":"144843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7586164474487305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6255542635917664},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.44235795736312866},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38837379217147827},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2521948218345642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586164474487305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6255542635917664},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.44235795736312866},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38837379217147827},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2521948218345642}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3345027","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3345027","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10366219.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:08b8e27933e7435cafcad313c4bfe927","is_oa":true,"landing_page_url":"https://doaj.org/article/08b8e27933e7435cafcad313c4bfe927","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 144831-144843 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3345027","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3345027","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/10005208/10366219.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G5761380661","display_name":null,"funder_award_id":"JP21H04900","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320317991","display_name":"National Institute for Japanese Language and Linguistics","ror":"https://ror.org/02caqc891"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389943413.pdf","grobid_xml":"https://content.openalex.org/works/W4389943413.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W914169429","https://openalex.org/W1498609987","https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W1997109056","https://openalex.org/W2006129368","https://openalex.org/W2093450784","https://openalex.org/W2097645910","https://openalex.org/W2100285470","https://openalex.org/W2108532241","https://openalex.org/W2166637769","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2471520273","https://openalex.org/W2775336875","https://openalex.org/W2794490148","https://openalex.org/W2889041236","https://openalex.org/W2935711438","https://openalex.org/W2952218014","https://openalex.org/W2963941778","https://openalex.org/W2963952344","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2972541922","https://openalex.org/W2998498479","https://openalex.org/W3015219411","https://openalex.org/W3015337486","https://openalex.org/W3035837245","https://openalex.org/W3036601975","https://openalex.org/W3043119899","https://openalex.org/W3049256661","https://openalex.org/W3081800019","https://openalex.org/W3092028330","https://openalex.org/W3095048608","https://openalex.org/W3096468295","https://openalex.org/W3097206152","https://openalex.org/W3099330747","https://openalex.org/W3113594615","https://openalex.org/W3140429000","https://openalex.org/W3161558238","https://openalex.org/W3163296124","https://openalex.org/W3183654341","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4200483526","https://openalex.org/W4221161734","https://openalex.org/W4224133928","https://openalex.org/W4225288502","https://openalex.org/W4225956675","https://openalex.org/W4281820413","https://openalex.org/W4296068974","https://openalex.org/W4307323391","https://openalex.org/W4375869170","https://openalex.org/W4381786045","https://openalex.org/W4385822341","https://openalex.org/W4385823191","https://openalex.org/W4386764866","https://openalex.org/W4394671563","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6729383884","https://openalex.org/W6741681139","https://openalex.org/W6747331233","https://openalex.org/W6750489868","https://openalex.org/W6752467913","https://openalex.org/W6771763809","https://openalex.org/W6773573674","https://openalex.org/W6779089044","https://openalex.org/W6779216093","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6787141514","https://openalex.org/W6790356757","https://openalex.org/W6798138677","https://openalex.org/W6803164887"],"related_works":["https://openalex.org/W2539919382","https://openalex.org/W22517275","https://openalex.org/W2042419400","https://openalex.org/W2122924390","https://openalex.org/W2064347532","https://openalex.org/W2589081144","https://openalex.org/W2171620991","https://openalex.org/W189256204","https://openalex.org/W2981428355","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Restoring":[0],"high-quality":[1],"speech":[2,56,79,117,128,138,151,212],"from":[3,61,183],"degraded":[4,109,150,184],"historical":[5,39,71,211],"recordings":[6],"is":[7,24,174],"crucial":[8],"for":[9,206],"the":[10,25,33,38,62,67,105,122,126,137,142,146,175,202,207],"preservation":[11],"of":[12,27,37,99,108,171,209],"cultural":[13],"and":[14,95,118,121,148,165],"endangered":[15],"linguistic":[16],"resources.":[17,213],"A":[18],"key":[19],"challenge":[20],"in":[21,70],"this":[22],"task":[23],"scarcity":[26],"paired":[28,47,85],"training":[29],"data":[30,48],"that":[31,81,197],"replicate":[32],"original":[34],"acoustic":[35,68,181],"conditions":[36],"audio.":[40],"While":[41],"previous":[42,203],"approaches":[43],"have":[44],"used":[45],"pseudo":[46],"generated":[49],"by":[50,158],"applying":[51],"various":[52],"distortions":[53,135,182],"to":[54,64,78,103,140,187,190],"clean":[55],"corpora,":[57],"their":[58],"limitations":[59],"stem":[60],"inability":[63],"authentically":[65],"simulate":[66],"variations":[69],"recordings.":[72],"We":[73,153],"propose":[74],"a":[75],"self-supervised":[76],"approach":[77,199,205],"restoration":[80,208],"does":[82],"not":[83],"require":[84],"corpora.":[86],"Our":[87],"model":[88,157,173],"has":[89],"three":[90],"main":[91],"modules:":[92],"analysis,":[93],"synthesis,":[94],"channel":[96,131],"modules,":[97],"all":[98],"which":[100,179],"are":[101],"designed":[102],"emulate":[104],"recording":[106],"process":[107],"audio":[110,176,185,192],"signals.":[111,152,193],"The":[112,130],"analysis":[113],"module":[114,124,132],"disentangles":[115],"undistorted":[116],"distortion":[119],"features,":[120],"synthesis":[123],"generates":[125],"restored":[127],"waveform.":[129],"then":[133],"introduces":[134],"into":[136],"waveform":[139],"compute":[141],"reconstruction":[143],"loss":[144],"between":[145],"input":[147],"output":[149],"further":[154],"improve":[155],"our":[156,172,198],"introducing":[159],"several":[160],"methods":[161],"including":[162],"dual":[163],"learning":[164],"semi-supervised":[166],"learning.":[167],"An":[168],"additional":[169],"feature":[170],"effect":[177],"transfer,":[178],"allows":[180],"signals":[186],"be":[188],"applied":[189],"arbitrary":[191],"Experimental":[194],"evaluations":[195],"demonstrated":[196],"significantly":[200],"outperforms":[201],"supervised":[204],"real":[210]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}