{"id":"https://openalex.org/W4385478010","doi":"https://doi.org/10.1109/icasspw59220.2023.10193459","title":"Zero-Shot Text-to-Speech Synthesis Conditioned Using Self-Supervised Speech Representation Model","display_name":"Zero-Shot Text-to-Speech Synthesis Conditioned Using Self-Supervised Speech Representation Model","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385478010","doi":"https://doi.org/10.1109/icasspw59220.2023.10193459"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/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/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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9959999918937683,"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/speech-recognition","display_name":"Speech recognition","score":0.7190847396850586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7088191509246826},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6160553097724915},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5700950622558594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5223856568336487},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5040992498397827},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.4594586193561554},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45565322041511536},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43854543566703796},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4378896951675415},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43711942434310913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4353974163532257},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42802417278289795},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17711582779884338},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08761656284332275}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7190847396850586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088191509246826},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6160553097724915},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5700950622558594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223856568336487},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5040992498397827},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4594586193561554},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45565322041511536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43854543566703796},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4378896951675415},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43711942434310913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4353974163532257},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42802417278289795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17711582779884338},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08761656284332275},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1596753861","https://openalex.org/W1692058958","https://openalex.org/W2114925438","https://openalex.org/W2398431249","https://openalex.org/W2746498480","https://openalex.org/W2746742816","https://openalex.org/W2794490148","https://openalex.org/W2801959488","https://openalex.org/W2890964092","https://openalex.org/W2933138175","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W3013020904","https://openalex.org/W3015645837","https://openalex.org/W3015826515","https://openalex.org/W3016021263","https://openalex.org/W3033411150","https://openalex.org/W3034729383","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3140429000","https://openalex.org/W3161627112","https://openalex.org/W3161704465","https://openalex.org/W3169739675","https://openalex.org/W3180374548","https://openalex.org/W3197580070","https://openalex.org/W3197830622","https://openalex.org/W3198667862","https://openalex.org/W3206495532","https://openalex.org/W3209059054","https://openalex.org/W4221153233","https://openalex.org/W4225096077","https://openalex.org/W4280542470","https://openalex.org/W4297841877","https://openalex.org/W4385245566","https://openalex.org/W6637425935","https://openalex.org/W6739901393","https://openalex.org/W6746700228","https://openalex.org/W6750489868","https://openalex.org/W6778823374","https://openalex.org/W6779469704","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796577156","https://openalex.org/W6839013216"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W596245619","https://openalex.org/W2254895521","https://openalex.org/W2251422729"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9,31,65,80],"zero-shot":[4],"text-to-speech":[5],"(TTS)":[6],"conditioned":[7,113],"by":[8,114],"self-supervised":[10,15],"speech-representation":[11],"model":[12,55],"acquired":[13],"through":[14],"learning":[16],"(SSL).":[17],"Conventional":[18],"methods":[19],"with":[20,64,129],"embedding":[21,58],"vectors":[22,59],"from":[23,60],"x-vector":[24],"or":[25],"global":[26],"style":[27],"tokens":[28],"still":[29],"have":[30],"gap":[32],"in":[33],"reproducing":[34],"the":[35,45,49,53,73,86,123],"speaker":[36,91],"characteristics":[37,92],"of":[38,44,52,68,76],"unseen":[39,108],"speakers.":[40],"A":[41],"novel":[42],"point":[43],"proposed":[46,124],"method":[47,125],"is":[48],"direct":[50],"use":[51],"SSL":[54],"to":[56,84,102],"obtain":[57,85],"speech":[61,128],"representations":[62],"trained":[63],"large":[66],"amount":[67],"data.":[69],"We":[70],"also":[71],"introduce":[72],"separate":[74],"conditioning":[75],"acoustic":[77],"features":[78],"and":[79,93,110,118,132],"phoneme":[81],"duration":[82],"predictor":[83],"disentangled":[87,97],"embeddings":[88,98],"between":[89],"rhythm-based":[90],"acoustic-feature-based":[94],"ones.":[95],"The":[96],"will":[99],"enable":[100],"us":[101],"achieve":[103,133],"better":[104],"reproduction":[105],"performance":[106],"for":[107],"speakers":[109],"rhythm":[111],"transfer":[112],"different":[115],"speeches.":[116],"Objective":[117],"subjective":[119],"evaluations":[120],"showed":[121],"that":[122],"can":[126],"synthesize":[127],"improved":[130],"similarity":[131],"speech-rhythm":[134],"transfer.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-08-03T00:00:00"}
