{"id":"https://openalex.org/W4392909919","doi":"https://doi.org/10.1109/icassp48485.2024.10448400","title":"Controllable Speaking Styles Using A Large Language Model","display_name":"Controllable Speaking Styles Using A Large Language Model","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909919","doi":"https://doi.org/10.1109/icassp48485.2024.10448400"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5049598035","display_name":"Atli Sigurgeirsson","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Atli Sigurgeirsson","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10851","last_page":"10855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7386999726295471,"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":0.7386999726295471,"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":0.7036580443382263},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40357697010040283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7036580443382263},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40357697010040283}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W2000633092","https://openalex.org/W2011976355","https://openalex.org/W2069859485","https://openalex.org/W2747874407","https://openalex.org/W2888844474","https://openalex.org/W2948238043","https://openalex.org/W3015645837","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W4212774754","https://openalex.org/W4283771593","https://openalex.org/W4292779060","https://openalex.org/W4297841867","https://openalex.org/W4318351475","https://openalex.org/W4375868833","https://openalex.org/W4375869257","https://openalex.org/W4385567149","https://openalex.org/W4398152753","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6763316926","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6790978476","https://openalex.org/W6809646742","https://openalex.org/W6810738896","https://openalex.org/W6849105126","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Reference-based":[0],"Text-to-Speech":[1],"(TTS)":[2],"models":[3,15,33,48,68],"can":[4,25,69,150],"generate":[5],"multiple,":[6],"prosodically-different":[7],"renditions":[8],"of":[9,86,156,164,183],"the":[10,146],"same":[11],"target":[12],"text.":[13],"Such":[14],"jointly":[16,120],"learn":[17],"a":[18,60,96,108,115,122,137,154,170,188],"latent":[19],"acoustic":[20],"space":[21],"during":[22,29,34],"training,":[23],"which":[24,43],"be":[26,70,104,151],"sampled":[27],"from":[28],"inference.":[30],"Controlling":[31],"these":[32],"inference":[35],"typically":[36,113],"requires":[37],"finding":[38],"an":[39,129],"appropriate":[40,168,180],"reference":[41,97],"utterance,":[42],"is":[44,177],"non-trivial.Large":[45],"generative":[46],"language":[47,62],"(LLMs)":[49],"have":[50],"shown":[51],"excellent":[52],"performance":[53],"in":[54,79,145,181],"various":[55],"language-related":[56],"tasks.":[57,76,157],"Given":[58],"only":[59,107],"natural":[61],"query":[63],"text":[64],"(the":[65],"\u2018prompt\u2019),":[66],"such":[67],"used":[71],"to":[72,131],"solve":[73],"specific,":[74],"context-dependent":[75],"Recent":[77],"work":[78],"TTS":[80,139],"has":[81],"attempted":[82],"similar":[83],"prompt-based":[84],"control":[85,163],"novel":[87],"speaking":[88,165],"style":[89],"generation.":[90],"Those":[91],"methods":[92,112],"do":[93],"not":[94],"require":[95,114],"utterance":[98],"and":[99],"can,":[100],"under":[101],"ideal":[102],"conditions,":[103],"controlled":[105],"with":[106],"prompt.":[109,147],"But":[110],"existing":[111],"prompt-labelled":[116],"speech":[117],"corpus":[118],"for":[119,136,153,169,187],"training":[121],"prompt-conditioned":[123],"encoder.In":[124],"contrast,":[125],"we":[126,159],"instead":[127],"employ":[128],"LLM":[130],"directly":[132],"suggest":[133],"prosodic":[134],"modifications":[135],"controllable":[138],"model,":[140],"using":[141],"contextual":[142],"information":[143],"provided":[144],"The":[148,174],"prompt":[149],"designed":[152],"multitude":[155],"Here,":[158],"give":[160],"two":[161],"demonstrations:":[162],"style;":[166],"prosody":[167],"given":[171],"dialogue":[172],"context.":[173],"proposed":[175],"method":[176],"rated":[178],"most":[179],"50%":[182],"cases":[184],"vs.":[185],"31%":[186],"baseline":[189],"model.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}