{"id":"https://openalex.org/W4398152753","doi":"https://doi.org/10.1109/taslp.2024.3402088","title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space With Natural Language Style Prompt","display_name":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space With Natural Language Style Prompt","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4398152753","doi":"https://doi.org/10.1109/taslp.2024.3402088"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3402088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402088","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China","Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-8905-224X","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China","Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0943-2446","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-1695-9000","affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-8712-9176","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4427-3532","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.486,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98961269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2913","last_page":"2925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9767000079154968,"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/T12031","display_name":"Speech and dialogue systems","score":0.9767000079154968,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9668999910354614,"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/T10028","display_name":"Topic Modeling","score":0.9611999988555908,"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/style","display_name":"Style (visual arts)","score":0.6620683670043945},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6581134796142578},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5829295516014099},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.46164220571517944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42685699462890625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.37155675888061523},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.16154199838638306},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1427059769630432},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.1321241855621338},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.0639534592628479}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6620683670043945},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6581134796142578},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5829295516014099},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46164220571517944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42685699462890625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37155675888061523},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.16154199838638306},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1427059769630432},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1321241855621338},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0639534592628479},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3402088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402088","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2007962718","https://openalex.org/W2058819080","https://openalex.org/W2067295501","https://openalex.org/W2107740512","https://openalex.org/W2107860279","https://openalex.org/W2130086727","https://openalex.org/W2133665775","https://openalex.org/W2157364932","https://openalex.org/W2752796333","https://openalex.org/W2908510526","https://openalex.org/W2963073614","https://openalex.org/W2963609956","https://openalex.org/W2969658393","https://openalex.org/W2972699445","https://openalex.org/W3156636935","https://openalex.org/W3174758275","https://openalex.org/W3180355996","https://openalex.org/W3196584150","https://openalex.org/W3197294703","https://openalex.org/W3197704090","https://openalex.org/W3198123658","https://openalex.org/W3198213150","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4210913346","https://openalex.org/W4226132755","https://openalex.org/W4281771798","https://openalex.org/W4297808394","https://openalex.org/W4307323391","https://openalex.org/W4312096566","https://openalex.org/W4312388283","https://openalex.org/W4312933868","https://openalex.org/W4313316128","https://openalex.org/W4313679638","https://openalex.org/W4367359628","https://openalex.org/W4372279529","https://openalex.org/W4375869257","https://openalex.org/W4381786045","https://openalex.org/W4382202703","https://openalex.org/W4385245566","https://openalex.org/W4385822534","https://openalex.org/W4388323056","https://openalex.org/W6631190155","https://openalex.org/W6679045638","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6752051073","https://openalex.org/W6752888775","https://openalex.org/W6757817989","https://openalex.org/W6762931180","https://openalex.org/W6766673545","https://openalex.org/W6769196770","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779459370","https://openalex.org/W6780218876","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6795807602","https://openalex.org/W6796163713","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6798447524","https://openalex.org/W6800989748","https://openalex.org/W6802805937","https://openalex.org/W6810926057","https://openalex.org/W6810940779","https://openalex.org/W6838510122","https://openalex.org/W6838815585","https://openalex.org/W6840815571","https://openalex.org/W6844194202","https://openalex.org/W6846143095","https://openalex.org/W6846176957","https://openalex.org/W6848735303","https://openalex.org/W6849416043","https://openalex.org/W6852581948"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W1567410843"],"abstract_inverted_index":{"Expressive":[0],"text-to-speech":[1],"(TTS)":[2],"aims":[3],"to":[4,11,22,30,60,126,155,171,197,222],"synthesize":[5,236],"speech":[6,15,69,72,240],"with":[7,45,76,241],"varying":[8],"speaking":[9,146,246],"styles":[10,33],"better":[12],"reflect":[13],"human":[14],"patterns.":[16],"In":[17],"this":[18,62],"study,":[19],"we":[20,65,89],"attempt":[21],"use":[23],"natural":[24,86,239],"language":[25],"as":[26],"a":[27,68,121,128,165],"style":[28,83,141,147,212,242],"prompt":[29],"control":[31,144],"the":[32,35,101,104,140,145,149,179,211,224,245],"in":[34,40,85,100,148,159],"synthetic":[36],"speech,e.g.,":[37],"\u201cSigh":[38],"tone":[39],"full":[41],"of":[42,103,112,228],"sad":[43],"mood":[44],"some":[46],"helpless":[47],"feeling\u201d.":[48],"Considering":[49],"that":[50,57,133,233],"there":[51],"is":[52,58,98],"no":[53],"existing":[54],"TTS":[55,93],"corpus":[56,70],"suitable":[59],"benchmark":[61],"novel":[63,99,122,166],"task,":[64],"first":[66],"construct":[67],"whose":[71],"samples":[73,249],"are":[74,250],"annotated":[75],"not":[77],"only":[78],"content":[79,205],"transcriptions":[80],"but":[81],"also":[82],"descriptions":[84],"language.":[87],"Then":[88],"propose":[90,120,154],"an":[91],"expressive":[92],"model,":[94],"named":[95],"InstructTTS,":[96],"which":[97],"sense":[102],"following":[105],"aspects:":[106],"(1)":[107],"We":[108,153,184],"fully":[109],"take":[110],"advantage":[111],"self-supervised":[113],"learning":[114,118],"and":[115,119,143,163,191,200,206,216,226,238],"cross-modal":[116],"metric":[117],"three-stage":[123],"training":[124,196],"procedure":[125],"obtain":[127],"robust":[129],"sentence":[130],"embedding":[131],"model":[132,156,170,195],"can":[134,235],"effectively":[135],"capture":[136],"semantic":[137],"information":[138,188,208],"from":[139,210],"prompts":[142,243],"generated":[150],"speech.":[151],"(2)":[152],"acoustic":[157,175,194],"features":[158],"discrete":[160,167],"latent":[161],"space":[162],"train":[164],"diffusion":[168],"probabilistic":[169],"generate":[172],"vector-quantized":[173],"(VQ)":[174],"tokens":[176],"rather":[177],"than":[178],"commonly-used":[180],"mel":[181],"spectrogram.":[182],"(3)":[183],"jointly":[185],"apply":[186],"mutual":[187],"(MI)":[189],"estimation":[190],"minimization":[192],"during":[193],"minimize":[198],"style-speaker":[199],"style-content":[201],"MI,":[202],"avoiding":[203],"possible":[204],"speaker":[207],"leakage":[209],"prompt.":[213],"Extensive":[214],"objective":[215],"subjective":[217],"evaluation":[218],"has":[219],"been":[220],"conducted":[221],"verify":[223],"effectiveness":[225],"expressiveness":[227],"InstructTTS.":[229],"Experimental":[230],"results":[231],"show":[232],"InstructTTS":[234],"high-fidelity":[237],"controlling":[244],"style.":[247],"Synthesized":[248],"available":[251],"online.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}