{"id":"https://openalex.org/W4416016739","doi":"https://doi.org/10.1145/3746252.3761311","title":"ParaStyleTTS: Toward Efficient and Robust Paralinguistic Style Control for Expressive Text-to-Speech Generation","display_name":"ParaStyleTTS: Toward Efficient and Robust Paralinguistic Style Control for Expressive Text-to-Speech Generation","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416016739","doi":"https://doi.org/10.1145/3746252.3761311"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.18308","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035505386","display_name":"Haowei Lou","orcid":"https://orcid.org/0009-0009-1359-872X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haowei Lou","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0009-1359-872X","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018724341","display_name":"Hye-Young Paik","orcid":"https://orcid.org/0000-0003-4425-7388"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hye-young Paik","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4425-7388","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042014818","display_name":"Wen Hu","orcid":"https://orcid.org/0000-0002-4076-1811"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wen Hu","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4076-1811","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["CSIRO's Data61, Sydney, NSW, Australia and University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"CSIRO's Data61, Sydney, NSW, Australia and University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571","https://openalex.org/I42894916"]}]}],"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":0.27596505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1979","last_page":"1988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2865999937057495,"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":0.2865999937057495,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.09059999883174896,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.08839999884366989,"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/paralanguage","display_name":"Paralanguage","score":0.8842999935150146},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5770999789237976},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.474700003862381},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41429999470710754},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.40389999747276306},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.3952000141143799},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.38659998774528503}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8842999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760699987411499},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5770999789237976},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38190001249313354},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.18308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.18308","pdf_url":"https://arxiv.org/pdf/2510.18308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.18308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.18308","pdf_url":"https://arxiv.org/pdf/2510.18308","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2760103357","https://openalex.org/W2948978827","https://openalex.org/W3163573274","https://openalex.org/W4231807801","https://openalex.org/W4367020198","https://openalex.org/W4372266552","https://openalex.org/W4405874014"],"related_works":[],"abstract_inverted_index":{"Controlling":[0],"speaking":[1,52,191],"style":[2,27,53,94,105,114,136],"in":[3,12,74],"text-to-speech":[4,201],"(TTS)":[5],"systems":[6,167],"has":[7],"become":[8],"a":[9,85,102,194],"growing":[10],"focus":[11],"both":[13],"academia":[14],"and":[15,38,66,76,87,111,119,128,142,150,176,187,196],"industry.":[16],"While":[17],"many":[18],"existing":[19],"approaches":[20],"rely":[21],"on":[22],"reference":[23],"audio":[24],"to":[25,35,50,68,164],"guide":[26],"generation,":[28],"such":[29,124],"methods":[30],"are":[31],"often":[32],"impractical":[33],"due":[34],"privacy":[36],"concerns":[37],"limited":[39],"accessibility.":[40],"More":[41],"recently,":[42],"large":[43],"language":[44,56],"models":[45],"(LLMs)":[46],"have":[47],"been":[48],"used":[49],"control":[51,95,121],"through":[54],"natural":[55],"prompts;":[57],"however,":[58],"their":[59,72],"high":[60],"computational":[61],"cost,":[62],"lack":[63],"of":[64],"interpretability,":[65],"sensitivity":[67],"prompt":[69,140],"phrasing":[70],"limit":[71],"applicability":[73],"real-time":[75],"resource-constrained":[77],"environments.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"propose":[83],"ParaStyleTTS,":[84],"lightweight":[86],"interpretable":[88],"TTS":[89],"framework":[90],"that":[91,108,156],"enables":[92],"expressive":[93],"from":[96],"text":[97],"prompts":[98],"alone.":[99],"ParaStyleTTS":[100,133,157,183],"features":[101],"novel":[103],"two-level":[104],"adaptation":[106],"architecture":[107],"separates":[109],"prosodic":[110],"paralinguistic":[112,190],"speech":[113,160],"modeling.":[115],"It":[116],"allows":[117],"fine-grained":[118],"robust":[120],"over":[122,189],"factors":[123],"as":[125],"emotion,":[126],"gender,":[127],"age.":[129],"Unlike":[130],"LLM-based":[131,166],"methods,":[132],"maintains":[134],"consistent":[135],"realization":[137],"across":[138],"varied":[139],"formulations":[141],"is":[143],"well-suited":[144],"for":[145,199],"real-world":[146],"applications,":[147],"including":[148],"on-device":[149],"low-resource":[151],"deployment.":[152],"Experimental":[153],"results":[154],"show":[155],"generates":[158],"high-quality":[159],"with":[161],"performance":[162],"comparable":[163],"state-of-the-art":[165],"while":[168],"being":[169],"30x":[170],"faster,":[171],"using":[172],"8x":[173],"fewer":[174],"parameters,":[175],"requiring":[177],"2.5x":[178],"less":[179],"CUDA":[180],"memory.":[181],"Moreover,":[182],"exhibits":[184],"superior":[185],"robustness":[186],"controllability":[188],"styles,":[192],"providing":[193],"practical":[195],"efficient":[197],"solution":[198],"style-controllable":[200],"generation.":[202],"Demo":[203],"can":[204,210],"be":[205,211],"found":[206,212],"at":[207,213],"https://parastyletts.github.io/ParaStyleTTS_Demo/.":[208],"Code":[209],"https://github.com/haoweilou/ParaStyleTTS.":[214]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-24T00:00:00"}