{"id":"https://openalex.org/W4221161734","doi":"https://doi.org/10.21437/interspeech.2022-298","title":"SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling","display_name":"SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221161734","doi":"https://doi.org/10.21437/interspeech.2022-298"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-298","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-298","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","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/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, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of 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, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of 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/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":"Tomohiko Nakamura","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of 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, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of 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":null,"apc_paid":null,"fwci":0.9719,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75794775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4406","last_page":"4410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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":0.9918000102043152,"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":0.9761999845504761,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6785165071487427},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5166921615600586},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4307973384857178},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09102699160575867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785165071487427},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5166921615600586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4307973384857178},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09102699160575867}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-298","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-298","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1406023492","display_name":null,"funder_award_id":"21H04900","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W914169429","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1997109056","https://openalex.org/W2006129368","https://openalex.org/W2093450784","https://openalex.org/W2100285470","https://openalex.org/W2166637769","https://openalex.org/W2194775991","https://openalex.org/W2471520273","https://openalex.org/W2546938941","https://openalex.org/W2806666542","https://openalex.org/W2889041236","https://openalex.org/W2952218014","https://openalex.org/W2963941778","https://openalex.org/W2963952344","https://openalex.org/W3000389243","https://openalex.org/W3015219411","https://openalex.org/W3015337486","https://openalex.org/W3028846133","https://openalex.org/W3030655016","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/W3113594615","https://openalex.org/W3163296124","https://openalex.org/W3169320628","https://openalex.org/W3183654341","https://openalex.org/W3203491020","https://openalex.org/W3209984917"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2359317704","https://openalex.org/W2367866479","https://openalex.org/W1496294449","https://openalex.org/W1570576710","https://openalex.org/W4308022734"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,67],"self-supervised":[3,68],"speech":[4,9,14,28,57,64,74,89,99,116,137,150],"restoration":[5,15,138],"method":[6,16,133],"without":[7],"paired":[8,19],"corpora.Because":[10],"the":[11,40,52,83,87,92,98,140],"previous":[12,141],"general":[13],"uses":[17],"artificial":[18],"data":[20,65,129],"created":[21],"by":[22],"applying":[23],"various":[24],"distortions":[25,35,96,111],"to":[26,97,119,147],"high-quality":[27,121],"corpora,":[29],"it":[30],"cannot":[31],"sufficiently":[32],"represent":[33],"acoustic":[34,110],"of":[36,44,55],"real":[37,62,128,148],"data,":[38],"limiting":[39],"applicability.Our":[41],"model":[42,101],"consists":[43],"analysis,":[45],"synthesis,":[46],"and":[47,58,76,91,117,127],"channel":[48,93],"modules":[49],"that":[50,131],"simulate":[51],"recording":[53],"process":[54],"degraded":[56,63,80,115,149],"is":[59],"trained":[60],"with":[61,124],"in":[66,107],"manner.The":[69],"analysis":[70],"module":[71,85,94],"extracts":[72],"distortionless":[73],"features":[75,78],"distortion":[77],"from":[79,114],"speech,":[81],"while":[82],"synthesis":[84],"synthesizes":[86],"restored":[88],"waveform,":[90],"adds":[95],"waveform.Our":[100],"also":[102],"enables":[103],"audio":[104],"effect":[105],"transfer,":[106],"which":[108],"only":[109],"are":[112],"extracted":[113],"added":[118],"arbitrary":[120],"audio.Experimental":[122],"evaluations":[123],"both":[125],"simulated":[126],"show":[130],"our":[132],"achieves":[134],"significantly":[135],"higher-quality":[136],"than":[139],"supervised":[142],"method,":[143],"suggesting":[144],"its":[145],"applicability":[146],"materials.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}