{"id":"https://openalex.org/W4410398715","doi":"https://doi.org/10.32473/flairs.38.1.138814","title":"Enhancing Expressiveness in Vocal Conversational Agents through Large Language Model-Generated Speech Synthesis Markup Language","display_name":"Enhancing Expressiveness in Vocal Conversational Agents through Large Language Model-Generated Speech Synthesis Markup Language","publication_year":2025,"publication_date":"2025-05-14","ids":{"openalex":"https://openalex.org/W4410398715","doi":"https://doi.org/10.32473/flairs.38.1.138814"},"language":"en","primary_location":{"id":"doi:10.32473/flairs.38.1.138814","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.38.1.138814","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/138814/144024","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journals.flvc.org/FLAIRS/article/download/138814/144024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004760366","display_name":"Joseph P. Salisbury","orcid":"https://orcid.org/0000-0002-9448-9024"},"institutions":[{"id":"https://openalex.org/I4210166787","display_name":"Riverside","ror":"https://ror.org/05y0cez87","country_code":"GB","type":"other","lineage":["https://openalex.org/I4210166787"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Joseph Salisbury","raw_affiliation_strings":["Riverside Research"],"raw_orcid":"https://orcid.org/0000-0002-9448-9024","affiliations":[{"raw_affiliation_string":"Riverside Research","institution_ids":["https://openalex.org/I4210166787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004760366"],"corresponding_institution_ids":["https://openalex.org/I4210166787"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26776708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8719000220298767,"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":0.8719000220298767,"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":0.810699999332428,"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":0.7850000262260437,"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/markup-language","display_name":"Markup language","score":0.8788601160049438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7333806157112122},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4214613735675812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4160316288471222},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3932070732116699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3544884920120239},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1336836814880371},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.10099667310714722}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.8788601160049438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333806157112122},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4214613735675812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4160316288471222},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3932070732116699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3544884920120239},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1336836814880371},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.10099667310714722},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.32473/flairs.38.1.138814","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.38.1.138814","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/138814/144024","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:94886b69f5b146f8bcc8c7215935a011","is_oa":true,"landing_page_url":"https://doaj.org/article/94886b69f5b146f8bcc8c7215935a011","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the International Florida Artificial Intelligence Research Society Conference, Vol 38, Iss 1 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.32473/flairs.38.1.138814","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.38.1.138814","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/138814/144024","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410398715.pdf","grobid_xml":"https://content.openalex.org/works/W4410398715.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1481503439","https://openalex.org/W1534597853","https://openalex.org/W2000476293","https://openalex.org/W2082494017","https://openalex.org/W2110585328","https://openalex.org/W2672179204","https://openalex.org/W2791548316","https://openalex.org/W2951293442","https://openalex.org/W3090087509","https://openalex.org/W4318907788","https://openalex.org/W4323537124","https://openalex.org/W4375869257","https://openalex.org/W4377121377","https://openalex.org/W4386346039","https://openalex.org/W4387993547","https://openalex.org/W4388327479","https://openalex.org/W4389263544","https://openalex.org/W4390722831","https://openalex.org/W4392011862","https://openalex.org/W4392719612","https://openalex.org/W6703294436","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6929438023"],"related_works":["https://openalex.org/W4385386698","https://openalex.org/W4388119604","https://openalex.org/W2954418080","https://openalex.org/W3121570353","https://openalex.org/W818235636","https://openalex.org/W4388119676","https://openalex.org/W1566913699","https://openalex.org/W2081328318","https://openalex.org/W2043722775","https://openalex.org/W1889092586"],"abstract_inverted_index":{"Advancements":[0],"in":[1,55],"speech":[2,19,33,88,101],"synthesis":[3],"have":[4],"enabled":[5],"more":[6],"natural":[7],"and":[8,46,61,111],"engaging":[9],"conversational":[10,130],"agents,":[11],"including":[12],"neural":[13],"text-to-speech":[14],"models":[15,75],"that":[16,71,105],"can":[17,31,58],"adjust":[18,32],"inflections":[20],"to":[21,51,77,98,116],"produce":[22],"distinct":[23],"vocal":[24,129],"styles.":[25,93],"For":[26],"example,":[27],"Azure":[28],"Neural":[29],"Voices":[30],"using":[34],"Speech":[35],"Synthesis":[36],"Markup":[37],"Language":[38],"(SSML)":[39],"style":[40,114],"tags,":[41,85],"such":[42],"as":[43],"\u201caffectionate,\u201d":[44],"\u201ccheerful,\u201d":[45],"\u201chopeful.\u201d":[47],"However,":[48],"determining":[49],"when":[50],"apply":[52,113],"these":[53],"tags":[54,115],"real-time":[56],"interactions":[57],"be":[59],"challenging":[60],"time-consuming.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,103],"present":[67],"a":[68],"prompt-based":[69],"approach":[70,122],"enables":[72],"large":[73],"language":[74],"(LLMs)":[76],"dynamically":[78],"stylize":[79],"their":[80],"responses":[81,107],"with":[82],"appropriate":[83],"SSML":[84],"enhancing":[86],"synthesized":[87],"expressiveness":[89],"across":[90],"34":[91],"different":[92],"Using":[94],"targeted":[95],"probes":[96],"designed":[97],"elicit":[99],"specific":[100],"styles,":[102],"demonstrate":[104],"LLM-generated":[106],"are":[108],"syntactically":[109],"well-formed":[110],"correctly":[112],"enhance":[117],"expressiveness.":[118],"This":[119],"simple,":[120],"customizable":[121],"facilitates":[123],"the":[124],"rapid":[125],"development":[126],"of":[127],"expressive":[128],"agents.":[131]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}