{"id":"https://openalex.org/W4408353590","doi":"https://doi.org/10.1109/icassp49660.2025.10890553","title":"Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting","display_name":"Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353590","doi":"https://doi.org/10.1109/icassp49660.2025.10890553"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5054823037","display_name":"Wooseok Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wooseok Han","raw_affiliation_strings":["AITRICS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AITRICS","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018777306","display_name":"Minki Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Minki Kang","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007599131","display_name":"Changhun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Changhun Kim","raw_affiliation_strings":["KAIST, AITRICS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, AITRICS","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086698569","display_name":"Eunho Yang","orcid":"https://orcid.org/0000-0003-2188-0169"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Eunho Yang","raw_affiliation_strings":["KAIST, AITRICS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, AITRICS","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6921,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96337538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"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":0.9959999918937683,"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":0.9959999918937683,"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/T12031","display_name":"Speech and dialogue systems","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9598000049591064,"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/prosody","display_name":"Prosody","score":0.8241232633590698},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7311264276504517},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7308327555656433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829331517219543}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8241232633590698},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7311264276504517},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7308327555656433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829331517219543}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2726515241","https://openalex.org/W2752796333","https://openalex.org/W2972359262","https://openalex.org/W3196001064","https://openalex.org/W4221159457","https://openalex.org/W4372259784","https://openalex.org/W4385822372","https://openalex.org/W4385823191","https://openalex.org/W4386072096","https://openalex.org/W6763832098","https://openalex.org/W6772349387","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6790220310","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6802200986","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6851724922","https://openalex.org/W6852870047"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"Speaker-adaptive":[0],"Text-to-Speech":[1],"(TTS)":[2],"synthesis":[3,103],"has":[4],"attracted":[5],"considerable":[6],"attention":[7],"due":[8],"to":[9,32,66,100,108],"its":[10],"broad":[11],"range":[12],"of":[13,39,60,80,88,119,125],"applications,":[14],"such":[15],"as":[16,67],"personalized":[17],"voice":[18],"assistant":[19],"services.":[20],"While":[21],"several":[22],"approaches":[23],"have":[24],"been":[25],"proposed,":[26],"they":[27],"often":[28],"exhibit":[29],"high":[30],"sensitivity":[31],"either":[33],"the":[34,37,77,86,89,102,117],"quantity":[35],"or":[36],"quality":[38],"target":[40,90,112,128],"speech":[41,129],"samples.":[42,69,113],"To":[43],"address":[44],"these":[45],"limitations,":[46],"we":[47],"introduce":[48],"Stable-TTS,":[49],"a":[50,57,61,95],"novel":[51],"speaker-adaptive":[52],"TTS":[53],"framework":[54],"that":[55],"leverages":[56],"small":[58],"subset":[59],"high-quality":[62,78],"pre-training":[63],"dataset,":[64],"referred":[65],"prior":[68,81,106],"Specifically,":[70],"Stable-TTS":[71,120],"achieves":[72],"prosody":[73,79],"consistency":[74],"by":[75],"leveraging":[76],"samples,":[82],"while":[83],"effectively":[84],"capturing":[85],"timbre":[87],"speaker.":[91],"Additionally,":[92],"it":[93],"employs":[94],"prior-preservation":[96],"loss":[97],"during":[98],"fine-tuning":[99],"maintain":[101],"ability":[104],"for":[105],"samples":[107,130],"prevent":[109],"overfitting":[110],"on":[111],"Extensive":[114],"experiments":[115],"demonstrate":[116],"effectiveness":[118],"even":[121],"under":[122],"limited":[123],"amounts":[124],"and":[126],"noisy":[127],".1":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}