{"id":"https://openalex.org/W4406611855","doi":"https://doi.org/10.1109/smc54092.2024.10831059","title":"Vrefine: A Self-Refinement Approach for Enhanced Clarity and Quality in Text-to-Speech Models","display_name":"Vrefine: A Self-Refinement Approach for Enhanced Clarity and Quality in Text-to-Speech Models","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611855","doi":"https://doi.org/10.1109/smc54092.2024.10831059"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5101940255","display_name":"Dongjin Huang","orcid":"https://orcid.org/0000-0002-6232-193X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjin Huang","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664245","display_name":"Yuhua Liu","orcid":"https://orcid.org/0000-0001-5861-7132"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhua Liu","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jixu Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixu Qian","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100413367","display_name":"Yanli Wang","orcid":"https://orcid.org/0000-0001-8126-1904"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanli Wang","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.28914549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"336","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9853000044822693,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9853000044822693,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9559999704360962,"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/T12031","display_name":"Speech and dialogue systems","score":0.9388999938964844,"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":0.7895403504371643},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.7362233996391296},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6227369904518127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5584321022033691},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5500407218933105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42866894602775574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895403504371643},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.7362233996391296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6227369904518127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5584321022033691},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5500407218933105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42866894602775574},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"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/smc54092.2024.10831059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2940703732","https://openalex.org/W2990594533","https://openalex.org/W3036601975","https://openalex.org/W3097945073","https://openalex.org/W3105867580","https://openalex.org/W3160799772","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225784348","https://openalex.org/W4297677272","https://openalex.org/W4327525621","https://openalex.org/W4362508231","https://openalex.org/W4383860339","https://openalex.org/W4387595589","https://openalex.org/W4391833199","https://openalex.org/W6739901393","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2086338133","https://openalex.org/W4367679314","https://openalex.org/W225526533","https://openalex.org/W2078361494","https://openalex.org/W2009234990","https://openalex.org/W4244083766","https://openalex.org/W2945718656","https://openalex.org/W2091016074","https://openalex.org/W2134615400","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Driven":[0],"by":[1,147,157,166],"advancements":[2],"in":[3],"the":[4,17,47,83,87,90,100,103,115,120,124,129,133,138,144,150,161,169,172,183],"Large":[5],"Language":[6],"Model":[7],"(LLM),":[8],"there":[9],"has":[10],"been":[11],"significant":[12],"global":[13],"attention":[14],"on":[15,41,76],"integrating":[16],"Generative":[18],"Pre-trained":[19],"Transformer":[20],"(GPT)":[21],"concept":[22],"into":[23],"Text-to-Speech":[24],"(TTS)":[25],"technologies.":[26],"However,":[27],"existing":[28],"TTS":[29,62,73,104],"models":[30],"face":[31],"issues":[32],"such":[33],"as":[34,65],"inconsistent":[35],"training":[36,125,184],"data":[37],"quality":[38,48,91,118],"and":[39,89,117,127,159],"reliance":[40],"autoregressive":[42],"models,":[43],"which":[44,67],"makes":[45],"controlling":[46],"of":[49,72,86,92,119,132,143,153,174],"audio":[50,134],"generation":[51,135],"challenging.":[52],"To":[53],"address":[54],"these":[55],"challenges,":[56],"this":[57],"study":[58],"introduces":[59],"a":[60,69,77,178],"novel":[61],"framework":[63,97],"known":[64],"TTS-Vrefine,":[66],"is":[68],"new":[70],"type":[71],"architecture":[74,170],"based":[75],"self-feedback":[78],"mechanism,":[79,180],"aimed":[80],"at":[81],"enhancing":[82],"inference":[84],"capabilities":[85],"model":[88,146],"generated":[93,111],"audio.":[94,121],"The":[95],"Vrefine":[96],"iteratively":[98],"refines":[99],"output,":[101],"allowing":[102],"system":[105],"to":[106],"self-train":[107],"using":[108],"its":[109],"own":[110],"data,":[112],"significantly":[113],"improving":[114,160],"clarity":[116],"It":[122],"expands":[123],"dataset":[126],"enhances":[128],"self-optimization":[130],"potential":[131],"model,":[136],"reducing":[137],"Word":[139],"Error":[140],"Rate":[141],"(WER)":[142],"base":[145],"2.4%,":[148],"increasing":[149],"Perceptual":[151],"Evaluation":[152],"Speech":[154],"Quality":[155],"(PESQ)":[156],"2.22%,":[158],"Short-Time":[162],"Objective":[163],"Intelligibility":[164],"(STOI)":[165],"4.55%.":[167],"Additionally,":[168],"optimizes":[171],"use":[173],"low-quality":[175],"resources":[176],"through":[177],"self-refinement":[179],"effectively":[181],"expanding":[182],"dataset.":[185]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}