{"id":"https://openalex.org/W4408353183","doi":"https://doi.org/10.1109/icassp49660.2025.10889756","title":"Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation","display_name":"Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353183","doi":"https://doi.org/10.1109/icassp49660.2025.10889756"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889756","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":"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/A5060967544","display_name":"Changjin Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changjin Han","raw_affiliation_strings":["DeepBrain AI,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI,Seoul,South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043828705","display_name":"Seokgi Lee","orcid":"https://orcid.org/0000-0002-8366-3584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seokgi Lee","raw_affiliation_strings":["DeepBrain AI,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI,Seoul,South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081937563","display_name":"Gyuhyeon Nam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyuhyeon Nam","raw_affiliation_strings":["DeepBrain AI,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI,Seoul,South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008455163","display_name":"Gyeongsu Chae","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyeongsu Chae","raw_affiliation_strings":["DeepBrain AI,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI,Seoul,South Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01681637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9965999722480774,"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":0.9965999722480774,"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":0.9883999824523926,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9514999985694885,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7356768846511841},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6435272693634033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5852645635604858},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416458249092102},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4246901869773865},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4209305942058563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22138717770576477},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0922655463218689}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7356768846511841},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6435272693634033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5852645635604858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416458249092102},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4246901869773865},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4209305942058563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22138717770576477},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0922655463218689},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889756","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":43,"referenced_works":["https://openalex.org/W2030582787","https://openalex.org/W2903739847","https://openalex.org/W2972359262","https://openalex.org/W3095410713","https://openalex.org/W3150572638","https://openalex.org/W3196001064","https://openalex.org/W3196584150","https://openalex.org/W3197541421","https://openalex.org/W3198020407","https://openalex.org/W3198213150","https://openalex.org/W4200300291","https://openalex.org/W4200464914","https://openalex.org/W4206319965","https://openalex.org/W4225956675","https://openalex.org/W4226332109","https://openalex.org/W4304099317","https://openalex.org/W4372259784","https://openalex.org/W4372260261","https://openalex.org/W4372260474","https://openalex.org/W4372341094","https://openalex.org/W4385823191","https://openalex.org/W4385993880","https://openalex.org/W4402112533","https://openalex.org/W4402672020","https://openalex.org/W4402981815","https://openalex.org/W6679045638","https://openalex.org/W6739901393","https://openalex.org/W6771467084","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6802527329","https://openalex.org/W6805710207","https://openalex.org/W6846143095","https://openalex.org/W6851724922","https://openalex.org/W6917585676","https://openalex.org/W6936129901"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W19748186","https://openalex.org/W2611973037","https://openalex.org/W2131825398","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"achieved":[3],"remarkable":[4],"success":[5],"in":[6,10,88,113],"text-to-speech":[7],"(TTS),":[8],"even":[9],"zero-shot":[11,65],"scenarios.":[12],"Recent":[13],"efforts":[14],"aim":[15],"to":[16,70],"address":[17],"the":[18,28,48,53,76,83,110],"trade-off":[19],"between":[20],"inference":[21],"speed":[22],"and":[23,118,133],"sound":[24],"quality,":[25],"often":[26],"considered":[27],"primary":[29],"drawback":[30],"of":[31,78,85,115],"diffusion":[32,54,79,89],"models.":[33],"However,":[34],"we":[35,60,91],"find":[36],"a":[37,63],"critical":[38],"mispronunciation":[39],"issue":[40],"is":[41],"being":[42],"overlooked.":[43],"Our":[44],"preliminary":[45],"study":[46],"reveals":[47],"unstable":[49],"pronunciation":[50,73,116],"resulting":[51],"from":[52],"process.":[55],"Based":[56],"on":[57,102],"this":[58],"observation,":[59],"introduce":[61],"StableForm-TTS,":[62],"novel":[64],"speech":[66],"synthesis":[67],"framework":[68],"designed":[69],"produce":[71],"robust":[72],"while":[74],"maintaining":[75],"advantages":[77],"modeling.":[80],"By":[81],"pioneering":[82],"adoption":[84],"source-filter":[86],"theory":[87],"TTS,":[90],"propose":[92],"an":[93],"elaborate":[94],"architecture":[95],"for":[96],"stable":[97],"formant":[98],"generation.":[99],"Experimental":[100],"results":[101],"unseen":[103],"speakers":[104],"show":[105],"that":[106],"our":[107,125],"model":[108,126,134],"outperforms":[109],"state-of-the-art":[111],"method":[112],"terms":[114],"accuracy":[117],"naturalness,":[119],"with":[120],"comparable":[121],"speaker":[122],"similarity.":[123],"Moreover,":[124],"demonstrates":[127],"effective":[128],"scalability":[129],"as":[130],"both":[131],"data":[132],"sizes":[135],"increase.":[136],"Audio":[137],"samples":[138],"are":[139],"available":[140],"online:":[141],"https://deepbrainai-research.github.io/stableformtts/.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}