{"id":"https://openalex.org/W4415743506","doi":"https://doi.org/10.1109/tpami.2025.3626793","title":"SpeechPalette: A Comprehensive Speech Editing Method for Text-Based Speech Editing, One-Shot TTS and Attributes Editing","display_name":"SpeechPalette: A Comprehensive Speech Editing Method for Text-Based Speech Editing, One-Shot TTS and Attributes Editing","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415743506","doi":"https://doi.org/10.1109/tpami.2025.3626793","pmid":"https://pubmed.ncbi.nlm.nih.gov/41171665"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3626793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3626793","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5071038184","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-1490-6973"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1490-6973","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2422-4618","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9598-1881","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":["Department of New Media and Communication, Tianjin University, Tianjin, China","Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of New Media and Communication, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083041690","display_name":"Dading Chong","orcid":"https://orcid.org/0000-0003-3495-522X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dading Chong","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Peking University, Beijing, China","Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3495-522X","affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407048","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-8054-3472"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Department of Electronics and Information Engineering, Soochow University, Suzhou, China","Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052785114","display_name":"Dongyang Dai","orcid":"https://orcid.org/0000-0001-5811-5781"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyang Dai","raw_affiliation_strings":["Department of Electronics and Information Engineering, Tsinghua University, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"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":0.14980077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"2596","last_page":"2609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7871000170707703,"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":0.7871000170707703,"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/T10863","display_name":"Voice and Speech Disorders","score":0.04910000041127205,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.027699999511241913,"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/leverage","display_name":"Leverage (statistics)","score":0.7028999924659729},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5117999911308289},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5062000155448914},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4032000005245209},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3682999908924103},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3547999858856201},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565999865531921},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7028999924659729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450999975204468},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3626793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3626793","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41171665","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41171665","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1202467192","display_name":null,"funder_award_id":"U21B2010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4467224230","display_name":null,"funder_award_id":"2025T180461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6859477402","display_name":null,"funder_award_id":"2025M771685","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7003438179","display_name":null,"funder_award_id":"62322120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1979932443","https://openalex.org/W2061620738","https://openalex.org/W2078169166","https://openalex.org/W2093824445","https://openalex.org/W2093840616","https://openalex.org/W2127141656","https://openalex.org/W2168510624","https://openalex.org/W2278339107","https://openalex.org/W2737697117","https://openalex.org/W2890964092","https://openalex.org/W2936002583","https://openalex.org/W2951310434","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2996414377","https://openalex.org/W3095035471","https://openalex.org/W3097531247","https://openalex.org/W3107271392","https://openalex.org/W3160438760","https://openalex.org/W3160614129","https://openalex.org/W3163677684","https://openalex.org/W3196475561","https://openalex.org/W3199044515","https://openalex.org/W4221142789","https://openalex.org/W4225264678","https://openalex.org/W4225596771","https://openalex.org/W4225701435","https://openalex.org/W4235716345","https://openalex.org/W4255442636","https://openalex.org/W4285124635","https://openalex.org/W4297841931","https://openalex.org/W4372260509","https://openalex.org/W4385571941","https://openalex.org/W4386057725","https://openalex.org/W4386117372","https://openalex.org/W4386180266","https://openalex.org/W4391147296","https://openalex.org/W4402672020"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"editing":[1,41,66,124],"has":[2],"garnered":[3],"more":[4,6,80],"and":[5,79,92,108,131,172],"attention":[7],"due":[8],"to":[9,46,57,101,176,195],"its":[10],"diverse":[11],"applications.":[12],"However,":[13],"existing":[14],"systems":[15],"often":[16],"require":[17],"substantial":[18],"manual":[19],"effort":[20],"or":[21],"have":[22],"limited":[23],"capabilities":[24],"in":[25,141],"attribute":[26],"editing,":[27],"imposing":[28],"significant":[29],"constraints.":[30],"In":[31],"this":[32],"work,":[33],"we":[34,96],"present":[35],"SpeechPalette,":[36],"a":[37,68,90,98,159,182],"comprehensive":[38,199],"high-quality":[39],"speech":[40,54,65,123,167],"method":[42,117,193],"that":[43],"allows":[44],"users":[45],"easily":[47],"modify":[48],"various":[49],"attributes":[50],"of":[51,184,191,205],"the":[52,61,82,103,106,188,203],"selected":[53],"segment":[55],"according":[56],"their":[58],"preferences.":[59],"Specifically,":[60],"proposed":[62,116,207],"model":[63,100],"approaches":[64],"from":[67,81],"decoupling":[69],"perspective,":[70],"disentangling":[71],"critical":[72],"information":[73],"such":[74],"as":[75],"text,":[76],"pitch,":[77],"duration":[78],"input":[83],"speech.":[84],"Then,":[85],"reconstruction":[86],"is":[87],"achieved":[88],"through":[89,153],"mask":[91],"prediction":[93],"mechanism.":[94],"Furthermore,":[95],"leverage":[97],"diffusion":[99],"predict":[102],"residuals":[104],"between":[105],"real":[107],"predicted":[109],"speech,":[110],"further":[111],"enhancing":[112],"synthesis":[113,151],"quality.":[114],"The":[115],"not":[118],"only":[119],"excels":[120],"at":[121],"text-based":[122],"but":[125],"also":[126,137],"handles":[127],"tasks":[128,185],"involving":[129],"pitch":[130],"speed":[132],"rate":[133],"adjustments.":[134],"Moreover,":[135],"it":[136],"demonstrates":[138],"remarkable":[139],"performance":[140,174,190],"one-shot":[142],"text-to-speech":[143],"scenarios.":[144],"While":[145],"recent":[146],"large-scale":[147],"models":[148],"achieve":[149],"impressive":[150],"quality":[152],"massive":[154],"computational":[155],"resources,":[156],"SpeechPalette":[157],"offers":[158],"balanced":[160],"approach":[161],"with":[162],"explicit":[163],"fine-grained":[164],"control":[165],"over":[166],"attributes,":[168],"practical":[169],"deployment":[170],"requirements,":[171],"competitive":[173],"relative":[175],"similarly-sized":[177],"systems.":[178,197],"Experimental":[179],"results":[180],"across":[181],"range":[183],"consistently":[186],"demonstrate":[187],"superior":[189],"our":[192,206],"compared":[194],"baseline":[196],"Additionally,":[198],"ablation":[200],"studies":[201],"validate":[202],"effectiveness":[204],"approach.":[208]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-31T00:00:00"}
