{"id":"https://openalex.org/W7138419101","doi":"https://doi.org/10.1609/aaai.v40i38.40505","title":"ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech","display_name":"ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138419101","doi":"https://doi.org/10.1609/aaai.v40i38.40505"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i38.40505","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40505","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i38.40505","any_repository_has_fulltext":false},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129640787","display_name":"Wen Hu","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129642260","display_name":"Lina Yao","orcid":null},"institutions":[{"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":["University of New South Wales\nCSIRO\u2019s Data61"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales\nCSIRO\u2019s Data61","institution_ids":["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":0.17525773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32311","last_page":"32319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.1882999986410141,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.1882999986410141,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.12630000710487366,"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":0.06509999930858612,"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":0.9126999974250793},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.545199990272522},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5278000235557556},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.41179999709129333},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2946999967098236}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9126999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930999755859375},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5278000235557556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46950000524520874},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4309000074863434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i38.40505","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40505","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/40505","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40505","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40505","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47629281878471375,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"representative":[1],"embeddings":[2,69],"for":[3,17,45,76,162],"different":[4],"types":[5],"of":[6],"speaking":[7,49,131],"styles,":[8],"such":[9,98],"as":[10,99],"emotion,":[11,100],"age,":[12,102],"and":[13,24,27,42,47,88,103,122,125,147,151,158],"gender,":[14,101],"is":[15],"critical":[16],"both":[18,120],"recognition":[19],"tasks":[20,29,97],"(e.g.,":[21,30],"cognitive":[22],"computing":[23],"human-computer":[25],"interaction)":[26],"generative":[28,116],"style-controllable":[31],"speech":[32,72],"generation).":[33],"In":[34],"this":[35],"work,":[36],"we":[37],"introduce":[38],"ParaMETA,":[39],"a":[40,90,156],"unified":[41],"flexible":[43],"framework":[44],"learning":[46],"controlling":[48],"styles":[50],"directly":[51],"from":[52],"speech.":[53],"Unlike":[54],"existing":[55],"methods":[56],"that":[57,139],"rely":[58],"on":[59],"single-task":[60],"models":[61],"or":[62],"cross-modal":[63],"alignment,":[64],"ParaMETA":[65,108,140],"learns":[66],"disentangled,":[67],"task-specific":[68],"by":[70],"projecting":[71],"into":[73],"dedicated":[74],"subspaces":[75],"each":[77],"style":[78,111,132],"type.":[79],"This":[80],"design":[81],"reduces":[82],"inter-task":[83],"interference,":[84],"mitigates":[85],"negative":[86],"transfer,":[87],"allows":[89,126],"single":[91],"model":[92,160],"to":[93,128],"handle":[94],"multiple":[95],"paralinguistic":[96],"nationality":[104],"classification.":[105],"Beyond":[106],"recognition,":[107],"enables":[109],"fine-grained":[110],"control":[112],"in":[113,144],"Text-To-Speech":[114],"(TTS)":[115],"models.":[117],"It":[118],"supports":[119],"speech-":[121],"text-based":[123],"prompting":[124],"users":[127],"modify":[129],"one":[130],"while":[133,154],"preserving":[134],"others.":[135],"Extensive":[136],"experiments":[137],"demonstrate":[138],"outperforms":[141],"strong":[142],"baselines":[143],"classification":[145],"accuracy":[146],"generates":[148],"more":[149],"natural":[150],"expressive":[152],"speech,":[153],"maintaining":[155],"lightweight":[157],"efficient":[159],"suitable":[161],"real-world":[163],"applications.":[164]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2026-03-18T00:00:00"}
