{"id":"https://openalex.org/W4408353942","doi":"https://doi.org/10.1109/icassp49660.2025.10889279","title":"Evidential-TTS: High Fidelity Zero-Shot Text-to-Speech Using Evidential Deep Learning","display_name":"Evidential-TTS: High Fidelity Zero-Shot Text-to-Speech Using Evidential Deep Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353942","doi":"https://doi.org/10.1109/icassp49660.2025.10889279"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889279","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/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014070","display_name":"Semin Kim","orcid":"https://orcid.org/0000-0003-3746-0863"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Semin Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":0.9991000294685364,"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":0.9991000294685364,"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":0.9929999709129333,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9818000197410583,"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/computer-science","display_name":"Computer science","score":0.6459580659866333},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5431023240089417},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5402599573135376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48649686574935913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4512932300567627},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.44267815351486206},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4302862286567688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3493354618549347},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1839112937450409},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09196385741233826},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07908445596694946},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06532654166221619},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05842334032058716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459580659866333},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5431023240089417},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5402599573135376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48649686574935913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4512932300567627},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.44267815351486206},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4302862286567688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3493354618549347},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1839112937450409},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09196385741233826},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07908445596694946},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06532654166221619},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05842334032058716},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889279","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":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4313021454","https://openalex.org/W4313120002","https://openalex.org/W4385245566","https://openalex.org/W4393241602","https://openalex.org/W4394597273","https://openalex.org/W4402112455","https://openalex.org/W6748865747","https://openalex.org/W6752745768","https://openalex.org/W6763291628","https://openalex.org/W6777694618","https://openalex.org/W6778883912","https://openalex.org/W6796464841","https://openalex.org/W6847363464","https://openalex.org/W6849367332","https://openalex.org/W6850334629","https://openalex.org/W6852581948","https://openalex.org/W6853188576","https://openalex.org/W6854494257","https://openalex.org/W6860273036","https://openalex.org/W6862144568"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W4224231624","https://openalex.org/W2319626700"],"abstract_inverted_index":{"We":[0],"propose":[1],"Evidential-TTS,":[2],"a":[3,18,82],"novel":[4],"zero-shot":[5],"text-to-speech":[6],"(TTS)":[7],"system":[8],"based":[9],"on":[10],"evidential":[11,34],"deep":[12],"learning":[13],"(EDL).":[14],"The":[15],"model":[16,69],"includes":[17],"length":[19],"regulator":[20],"to":[21,37],"ensure":[22],"precise":[23],"alignment":[24],"between":[25],"phonemes":[26],"and":[27,104],"acoustic":[28,44],"tokens.":[29],"This":[30,79],"module":[31],"allows":[32],"the":[33,39,72,111,118],"token":[35],"generator":[36],"convert":[38],"aligned":[40],"phoneme":[41],"sequence":[42],"into":[43,71],"tokens":[45],"using":[46,58],"iterative":[47],"parallel":[48],"decoding":[49],"(IPD).":[50],"However,":[51],"IPD":[52],"often":[53],"suffers":[54],"from":[55],"overconfidence":[56],"when":[57],"categorical":[59],"probabilities":[60],"as":[61],"confidence":[62],"scores.":[63],"To":[64],"address":[65],"this,":[66],"we":[67],"introduce":[68],"uncertainty":[70,80,114],"sampling":[73,85,119],"process,":[74],"quantified":[75],"through":[76],"EDL":[77],"optimization.":[78],"provides":[81],"more":[83],"reliable":[84],"path":[86],"for":[87],"high-quality":[88],"speech":[89,102],"generation.":[90],"Experimental":[91],"results":[92],"show":[93],"that":[94],"Evidential-TTS":[95],"outperforms":[96],"existing":[97],"models":[98],"in":[99,116],"terms":[100],"of":[101,113,121],"naturalness":[103],"intelligibility.":[105],"An":[106],"ablation":[107],"study":[108],"further":[109],"demonstrates":[110],"importance":[112],"estimation":[115],"guiding":[117],"trajectory":[120],"IPD.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}