{"id":"https://openalex.org/W4405709630","doi":"https://doi.org/10.1109/iscslp63861.2024.10800531","title":"LLM-Based Expressive Text-to-Speech Synthesizer with Style and Timbre Disentanglement","display_name":"LLM-Based Expressive Text-to-Speech Synthesizer with Style and Timbre Disentanglement","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709630","doi":"https://doi.org/10.1109/iscslp63861.2024.10800531"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100989234","display_name":"Yuanyuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanyuan Zhu","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083005075","display_name":"Jiaxu He","orcid":null},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu He","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623017","display_name":"Rui Jing","orcid":"https://orcid.org/0009-0001-2039-839X"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihao Jing","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080376457","display_name":"Yaodong Song","orcid":"https://orcid.org/0000-0002-9586-7963"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Song","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042693941","display_name":"Jie Lian","orcid":"https://orcid.org/0000-0003-1033-3805"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Lian","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-lei Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454072","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-1558-8623"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom,Beijing","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100989234"],"corresponding_institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"],"apc_list":null,"apc_paid":null,"fwci":1.1586,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82961879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"596","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9912999868392944,"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":0.9912999868392944,"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":0.9419000148773193,"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":0.9405999779701233,"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/timbre","display_name":"Timbre","score":0.8234050869941711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682048439979553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5980499386787415},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5328389406204224},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.43339988589286804},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.05260813236236572},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.0338611900806427}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8234050869941711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682048439979553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5980499386787415},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5328389406204224},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.43339988589286804},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.05260813236236572},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0338611900806427},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2964243274","https://openalex.org/W3097945073","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4385822407","https://openalex.org/W4393147067","https://openalex.org/W4402111239","https://openalex.org/W4402112533","https://openalex.org/W4402669711","https://openalex.org/W4402672020"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930"],"abstract_inverted_index":{"The":[0],"ICACG":[1],"challenge":[2],"Track":[3,160],"1":[4,161],"requires":[5],"to":[6,49,72,78,133],"generate":[7],"the":[8,32,51,57,74,79,88,96,99,112,135,154],"target":[9,80,100],"speaker":[10,18,81,85],"audios":[11],"with":[12],"high":[13,106],"naturalness":[14],"under":[15],"extremely":[16],"limited":[17],"dataset.":[19],"To":[20],"achieve":[21,104],"this":[22],"goal,":[23],"we":[24],"introduce":[25],"a":[26,67,105,125,139],"novel":[27,126],"text-to-speech":[28],"synthesizer":[29],"which":[30,54],"disentangles":[31],"style":[33,58],"and":[34,118,152,175],"tim-bre":[35],"information":[36,59],"in":[37,63,76,146,157],"cascade":[38],"approach.":[39],"Firstly,":[40],"an":[41],"auto-regressive":[42],"large":[43,117],"language":[44],"model":[45],"(LLM)":[46],"is":[47,70,121,130],"applied":[48],"complete":[50],"text-to-token":[52],"generation,":[53],"can":[55,92],"capture":[56],"from":[60],"audio":[61,91],"prompt":[62],"zero-shot":[64],"mode.":[65],"Subsequently,":[66],"variational":[68],"generator":[69],"used":[71],"reconstruct":[73],"mel-spectrogram":[75],"corresponding":[77],"timbre":[82,97],"conditioned":[83],"on":[84],"embedding.":[86],"Therefore,":[87],"final":[89],"synthesized":[90],"not":[93],"only":[94],"contain":[95],"of":[98,108,114,148],"speaker,":[101],"but":[102],"also":[103,131],"degree":[107],"expressiveness":[109],"by":[110],"utilizing":[111],"capabilities":[113],"LLM.":[115],"Since":[116],"diverse":[119],"data":[120,127],"necessary":[122],"for":[123],"training,":[124],"processing":[128],"pipeline":[129],"proposed":[132],"process":[134],"collected":[136],"data.":[137],"As":[138],"result,":[140],"our":[141],"system":[142],"achieved":[143],"great":[144],"performance":[145],"terms":[147],"expressive":[149],"speech":[150],"synthesis":[151],"ranked":[153],"first":[155],"place":[156],"ICAGC":[158],"2024":[159],"over":[162],"all":[163],"five":[164],"evaluation":[165],"metrics:":[166],"3.89":[167,173],"Quality,":[168],"3.83":[169],"Similarity,":[170],"3.85":[171],"Emotion,":[172],"MOS(avg)":[174],"0.22":[176],"MOS":[177],"(std).":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}