{"id":"https://openalex.org/W4408862231","doi":"https://doi.org/10.1109/icce63647.2025.10930170","title":"Briefing of Text-to-Speech Trends Toward Zero-Shot Multi-Speaker Synthesis","display_name":"Briefing of Text-to-Speech Trends Toward Zero-Shot Multi-Speaker Synthesis","publication_year":2025,"publication_date":"2025-01-11","ids":{"openalex":"https://openalex.org/W4408862231","doi":"https://doi.org/10.1109/icce63647.2025.10930170"},"language":"en","primary_location":{"id":"doi:10.1109/icce63647.2025.10930170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce63647.2025.10930170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Consumer Electronics (ICCE)","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":null,"display_name":"Dahyun Song","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dahyun Song","raw_affiliation_strings":["Chung-Ang University,Dept. Artificial Intelligence,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Dept. Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100744043","display_name":"Jaesung Lee","orcid":"https://orcid.org/0000-0002-3757-3510"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaesung Lee","raw_affiliation_strings":["Chung-Ang University,Dept. Artificial Intelligence,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Dept. Artificial Intelligence,Seoul,South Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02269958,"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":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919999837875366,"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":0.9919999837875366,"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":0.628264844417572},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6205627918243408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5877526998519897},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5122022032737732},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.47620949149131775},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45168811082839966},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18745830655097961},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08937466144561768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.628264844417572},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6205627918243408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5877526998519897},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5122022032737732},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.47620949149131775},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45168811082839966},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18745830655097961},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08937466144561768},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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/icce63647.2025.10930170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce63647.2025.10930170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2903739847","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3095545636","https://openalex.org/W3160919572","https://openalex.org/W4221156079","https://openalex.org/W4377079685","https://openalex.org/W6738277540","https://openalex.org/W6749489859","https://openalex.org/W6749555683","https://openalex.org/W6752888775","https://openalex.org/W6755300632","https://openalex.org/W6763832098","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6797417463","https://openalex.org/W6805710207","https://openalex.org/W6810528595","https://openalex.org/W6846143095"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"This":[0],"paper":[1],"reviews":[2],"advancements":[3],"in":[4,115,126],"Text-to-Speech":[5],"(TTS)":[6],"systems":[7,15],"and":[8,49,72,92,100,111,119],"focuses":[9],"on":[10,44],"the":[11,74,106],"evolution":[12],"from":[13],"single-speaker":[14,23],"to":[16],"Zero-Shot":[17],"Multi-Speaker":[18],"TTS":[19,24],"(ZS-TTS)":[20],"systems.":[21],"Traditional":[22],"models":[25,38],"require":[26],"retraining":[27],"whenever":[28],"a":[29,54,66],"new":[30],"speaker":[31,88],"is":[32,53],"introduced,":[33],"which":[34],"limits":[35],"scalability.":[36],"Multi-speaker":[37],"address":[39],"this":[40,80],"issue":[41],"but":[42],"rely":[43],"large":[45],"amounts":[46],"of":[47,69,108],"data":[48],"computational":[50],"resources.":[51],"ZS-TTS":[52],"recent":[55],"innovation":[56],"that":[57],"synthesizes":[58],"natural":[59],"speech":[60],"for":[61,76,123],"unseen":[62],"speakers":[63],"using":[64],"only":[65],"few":[67],"seconds":[68],"reference":[70],"audio":[71],"eliminates":[73],"need":[75],"additional":[77],"fine-tuning.":[78],"In":[79],"paper,":[81],"we":[82],"introduce":[83],"important":[84],"methods":[85],"such":[86],"as":[87],"embedding,":[89],"GAN-based":[90],"models,":[91],"transformers,":[93],"explaining":[94],"how":[95],"these":[96],"approaches":[97],"improve":[98],"efficiency":[99],"voice":[101],"quality.":[102],"It":[103],"also":[104],"examines":[105],"challenges":[107],"inference":[109],"speed":[110],"model":[112],"scalability,":[113],"especially":[114],"edge":[116],"computing":[117],"environments,":[118],"suggests":[120],"potential":[121],"directions":[122],"future":[124],"research":[125],"TTS.":[127]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}