{"id":"https://openalex.org/W4392905338","doi":"https://doi.org/10.1109/ccnc51664.2024.10454740","title":"Optimization for Low-Resource Speaker Adaptation in End-to-End Text-to-Speech","display_name":"Optimization for Low-Resource Speaker Adaptation in End-to-End Text-to-Speech","publication_year":2024,"publication_date":"2024-01-06","ids":{"openalex":"https://openalex.org/W4392905338","doi":"https://doi.org/10.1109/ccnc51664.2024.10454740"},"language":"en","primary_location":{"id":"doi:10.1109/ccnc51664.2024.10454740","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccnc51664.2024.10454740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","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/A5113145244","display_name":"Changi Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Changi Hong","raw_affiliation_strings":["Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062121707","display_name":"Jung Hyuk Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Hyuk Lee","raw_affiliation_strings":["Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056743652","display_name":"Moongu Jeon","orcid":"https://orcid.org/0000-0002-2775-7789"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Moongu Jeon","raw_affiliation_strings":["Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005"],"affiliations":[{"raw_affiliation_string":"Gwangju Institute of Science and Technology (GIST),Gwangju,South Korea,61005","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113145244"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02633889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1060","last_page":"1061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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":0.9965000152587891,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7996783256530762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7744321823120117},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6404423713684082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5762099027633667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2161460816860199},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05639258027076721}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7996783256530762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744321823120117},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6404423713684082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5762099027633667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2161460816860199},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05639258027076721},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccnc51664.2024.10454740","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccnc51664.2024.10454740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 21st Consumer Communications & Networking Conference (CCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3090254849","https://openalex.org/W3097777922","https://openalex.org/W3161480375","https://openalex.org/W3168867926","https://openalex.org/W3169905056","https://openalex.org/W3205949070","https://openalex.org/W6783527727","https://openalex.org/W6796464841","https://openalex.org/W6796581206","https://openalex.org/W6802744804"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Fine":[0],"tuning":[1,164],"of":[2,10,19,33,36,44,48,52,56,95,107,115,121,165,168,174,177,181],"an":[3,68],"end-to-end":[4],"text-to-speech":[5],"(TTS)":[6],"model":[7,37,60,161,170],"is":[8,26],"one":[9],"the":[11,17,23,31,42,50,57,80,92,96,108,149,158,163,169],"most":[12],"common":[13],"methods":[14],"for":[15,71,86],"optimizing":[16],"performance":[18],"target":[20],"speakers.":[21],"However,":[22],"fine-tuning":[24],"process":[25],"time":[27],"consuming":[28],"and":[29,104,137,179],"necessitates":[30],"storage":[32,43],"large":[34,46],"number":[35,47,120],"parameters.":[38],"Therefore,":[39],"to":[40,62,157],"reduce":[41],"a":[45,76],"parameters,":[49],"optimization":[51,69,151],"only":[53,166],"partial":[54],"components":[55],"entire":[58],"TTS":[59,77],"needs":[61],"be":[63],"considered.":[64],"This":[65],"paper":[66],"proposes":[67],"method":[70,152],"low-resource":[72],"speaker":[73,101,128],"adaptation":[74],"on":[75,127],"model,":[78,98],"i.e.,":[79],"Variational":[81],"Inference":[82],"with":[83,118,162,172],"Adversarial":[84],"Learning":[85],"End-to-End":[87],"Text-to-Speech":[88],"(VITS)":[89],"model.":[90],"Particu-larly,":[91],"encoder":[93,110],"modules":[94],"VITS":[97],"flow":[99],"network,":[100],"embedding":[102,129],"layer,":[103],"projection":[105],"layer":[106],"text":[109],"are":[111,124],"optimized.":[112],"The":[113,145],"performances":[114],"fine-tuned":[116,160],"models":[117],"varying":[119],"optimized":[122],"parameters":[123,171],"compared":[125,156],"based":[126],"cosine":[130],"similarity":[131],"(SECS),":[132],"word":[133],"error":[134],"rate":[135],"(WER),":[136],"deep":[138],"noise":[139],"suppression":[140],"mean":[141],"opinion":[142],"score":[143],"(DNSMOS).":[144],"results":[146],"show":[147],"that":[148],"proposed":[150],"exhibits":[153],"reasonable":[154],"quality":[155],"fully":[159],"9%":[167],"SECS":[173],"0.630,":[175],"WER":[176],"2.4%,":[178],"DNSMOS":[180],"3.44":[182]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}