{"id":"https://openalex.org/W4386764866","doi":"https://doi.org/10.1109/waspaa58266.2023.10248089","title":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","display_name":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764866","doi":"https://doi.org/10.1109/waspaa58266.2023.10248089"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107006573","display_name":"Yifan Ding","orcid":"https://orcid.org/0009-0001-4352-5427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Ding","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I127317711","display_name":"Tokyo University of Agriculture","ror":"https://ror.org/05crbcr45","country_code":"JP","type":"education","lineage":["https://openalex.org/I127317711"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Tokyo University of Agriculture & Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture & Technology,Japan","institution_ids":["https://openalex.org/I127317711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111040545","display_name":"Nobuyuki Morioka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyuki Morioka","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092339709","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0007-7826-1306"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750907","display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-4201-9645"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024316712","display_name":"Ankur Bapna","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Bapna","raw_affiliation_strings":["Google,USA","Google, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google,Japan","Google, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Japan","institution_ids":[]},{"raw_affiliation_string":"Google, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.7939506769180298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.642025351524353},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5113930106163025},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.5054202079772949},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4740276634693146},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4738866686820984},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4682038426399231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4553114175796509},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44988659024238586},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.42413362860679626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41639310121536255},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4158942401409149},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41266560554504395},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3973965644836426},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39127781987190247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08209684491157532},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061804771423339844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939506769180298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.642025351524353},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5113930106163025},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.5054202079772949},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4740276634693146},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4738866686820984},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4682038426399231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553114175796509},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44988659024238586},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.42413362860679626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41639310121536255},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4158942401409149},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41266560554504395},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3973965644836426},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39127781987190247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08209684491157532},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061804771423339844},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W2117678320","https://openalex.org/W2144786298","https://openalex.org/W2164502538","https://openalex.org/W2519091744","https://openalex.org/W2747732471","https://openalex.org/W2760103357","https://openalex.org/W2808706139","https://openalex.org/W2892620417","https://openalex.org/W2907262790","https://openalex.org/W2962866211","https://openalex.org/W2963952344","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972970915","https://openalex.org/W2998498479","https://openalex.org/W3015338123","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3043119899","https://openalex.org/W3091928890","https://openalex.org/W3092028330","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3123097577","https://openalex.org/W3139918052","https://openalex.org/W3140429000","https://openalex.org/W3161541317","https://openalex.org/W3177067699","https://openalex.org/W3197324626","https://openalex.org/W3197845638","https://openalex.org/W3203491020","https://openalex.org/W4200483526","https://openalex.org/W4221141648","https://openalex.org/W4221161734","https://openalex.org/W4221161761","https://openalex.org/W4225566824","https://openalex.org/W4226033575","https://openalex.org/W4232282348","https://openalex.org/W4281736089","https://openalex.org/W4281820413","https://openalex.org/W4283023481","https://openalex.org/W4289383906","https://openalex.org/W4296068407","https://openalex.org/W4298580827","https://openalex.org/W4319862245","https://openalex.org/W6741681139","https://openalex.org/W6748409065","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6755300632","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783867762","https://openalex.org/W6784545093","https://openalex.org/W6784614252","https://openalex.org/W6791904447","https://openalex.org/W6802017037","https://openalex.org/W6810673746","https://openalex.org/W6838843145","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2138847091","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"Speech":[0],"restoration":[1],"(SR)":[2],"is":[3,95],"a":[4,19,29,65,77,86,107],"task":[5],"of":[6,36],"converting":[7,44],"degraded":[8],"speech":[9,41,45,66,114],"signals":[10],"into":[11],"high-quality":[12,37,108],"ones.":[13],"In":[14],"this":[15],"study,":[16],"we":[17,62],"propose":[18],"robust":[20,58,96],"SR":[21,31,56],"model":[22,57,111],"called":[23],"Miipher,":[24],"and":[25,75,101],"apply":[26],"Miipher":[27,93],"to":[28,51,105],"new":[30],"application:":[32],"increasing":[33],"the":[34,49,72,118],"amount":[35],"training":[38],"data":[39],"for":[40,71],"generation":[42],"by":[43],"samples":[46,115,121],"collected":[47,116],"from":[48,69,81,112,117],"Web":[50],"studio-quality.":[52],"To":[53],"make":[54],"our":[55,125],"against":[59,97],"various":[60,98],"degradation,":[61],"use":[63],"(i)":[64,94],"representation":[67,79],"extracted":[68,80],"w2v-BERT":[70],"input":[73],"feature,":[74],"(ii)":[76,102],"text":[78],"transcripts":[82],"via":[83],"PnG-BERT":[84],"as":[85],"linguistic":[87],"conditioning":[88],"feature.":[89],"Experiments":[90],"show":[91],"that":[92],"audio":[99],"degradation":[100],"enable":[103],"us":[104],"train":[106],"text-to-speech":[109],"(TTS)":[110],"restored":[113],"Web.":[119],"Audio":[120],"are":[122],"available":[123],"at":[124],"demo":[126],"page:":[127],"google.github.io/df-conformer/miipher/.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}