{"id":"https://openalex.org/W4392910802","doi":"https://doi.org/10.1109/icassp48485.2024.10447809","title":"Noise-Robust Zero-Shot Text-to-Speech Synthesis Conditioned on Self-Supervised Speech-Representation Model with Adapters","display_name":"Noise-Robust Zero-Shot Text-to-Speech Synthesis Conditioned on Self-Supervised Speech-Representation Model with Adapters","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910802","doi":"https://doi.org/10.1109/icassp48485.2024.10447809"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101528279","display_name":"Ken\u2010ichi Fujita","orcid":"https://orcid.org/0000-0002-1575-6690"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi Fujita","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076754533","display_name":"Hiroki Kanagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Kanagawa","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11471","last_page":"11475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9848999977111816,"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":0.9848999977111816,"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/speech-recognition","display_name":"Speech recognition","score":0.7054222822189331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6761782169342041},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6529507637023926},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5877055525779724},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5416136384010315},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4330589473247528},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42721351981163025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4160480797290802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3226141333580017},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08975815773010254}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7054222822189331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761782169342041},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6529507637023926},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5877055525779724},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5416136384010315},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4330589473247528},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42721351981163025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4160480797290802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3226141333580017},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08975815773010254},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1596753861","https://openalex.org/W2060277733","https://openalex.org/W2114925438","https://openalex.org/W2219249508","https://openalex.org/W2746498480","https://openalex.org/W2746742816","https://openalex.org/W2801959488","https://openalex.org/W2890964092","https://openalex.org/W2952218014","https://openalex.org/W2964243274","https://openalex.org/W3015826515","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3099330747","https://openalex.org/W3161704465","https://openalex.org/W3163906773","https://openalex.org/W3197830622","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221146604","https://openalex.org/W4224612669","https://openalex.org/W4225096077","https://openalex.org/W4225323055","https://openalex.org/W4226390724","https://openalex.org/W4226403810","https://openalex.org/W4296069295","https://openalex.org/W4313679638","https://openalex.org/W4319862642","https://openalex.org/W4385245566","https://openalex.org/W4385478010","https://openalex.org/W4385484947","https://openalex.org/W4385822534","https://openalex.org/W4385823298","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6759579507","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6810334672","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W127416991"],"abstract_inverted_index":{"The":[0],"zero-shot":[1,48,88],"text-to-speech":[2],"(TTS)":[3],"method,":[4],"based":[5],"on":[6],"speaker":[7,21],"embeddings":[8],"extracted":[9],"from":[10,29],"reference":[11,37,67,96,116],"speech":[12,17,32,38,78,92],"using":[13,65],"self-supervised":[14],"learning":[15],"(SSL)":[16],"representations,":[18],"can":[19],"reproduce":[20],"characteristics":[22],"very":[23],"accurately.":[24],"However,":[25],"this":[26,42],"approach":[27],"suffers":[28],"degradation":[30],"in":[31,115,121],"synthesis":[33,93],"quality":[34],"when":[35],"the":[36,55,62,99,107],"contains":[39],"noise.":[40],"In":[41,69],"paper,":[43],"we":[44,59,75,104],"propose":[45],"a":[46,77],"noise-robust":[47],"TTS":[49,63,89],"method.":[50],"We":[51],"incorporated":[52],"adapters":[53],"into":[54],"SSL":[56],"model,":[57],"which":[58],"fine-tuned":[60],"with":[61,94,123],"model":[64],"noisy":[66,95],"speech.":[68,97],"addition,":[70],"to":[71,113],"further":[72],"improve":[73],"performance,":[74],"adopted":[76],"enhancement":[79],"(SE)":[80],"front-end.":[81],"With":[82],"these":[83],"improvements,":[84],"our":[85],"proposed":[86,108],"SSL-based":[87],"achieved":[90],"high-quality":[91],"Through":[98],"objective":[100],"and":[101,118],"subjective":[102],"evaluations,":[103],"confirmed":[105],"that":[106],"method":[109],"is":[110],"highly":[111],"robust":[112],"noise":[114],"speech,":[117],"effectively":[119],"works":[120],"combination":[122],"SE.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
