{"id":"https://openalex.org/W7164847683","doi":"https://doi.org/10.1145/3805622.3810570","title":"ATRIE: Adaptive Tuning for Robust Inference and Emotion in Persona-Driven Speech Synthesis","display_name":"ATRIE: Adaptive Tuning for Robust Inference and Emotion in Persona-Driven Speech Synthesis","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164847683","doi":"https://doi.org/10.1145/3805622.3810570"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810570","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810570","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810570","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086188383","display_name":"Aoduo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoduo Li","raw_affiliation_strings":["Guangdong University of Technology, Jieyang, China"],"raw_orcid":"https://orcid.org/0009-0003-2385-5343","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Jieyang, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137568306","display_name":"Haoran Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Lv","raw_affiliation_strings":["Guangdong University of Technology, Jieyang, China"],"raw_orcid":"https://orcid.org/0009-0001-3310-6835","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Jieyang, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134276267","display_name":"Hongjian Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjian Xu","raw_affiliation_strings":["Guangdong University of Technology, Jieyang, China"],"raw_orcid":"https://orcid.org/0009-0009-4463-3364","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Jieyang, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008479237","display_name":"S Li","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengmin Li","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-6511-7652","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048527794","display_name":"Sihao Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sihao Qin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-0097-5297","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004636","display_name":"Zimeng Li","orcid":"https://orcid.org/0000-0003-2798-3134"},"institutions":[{"id":"https://openalex.org/I182722699","display_name":"Shenzhen Polytechnic University","ror":"https://ror.org/00d2w9g53","country_code":"CN","type":"education","lineage":["https://openalex.org/I182722699"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zimeng Li","raw_affiliation_strings":["Shenzhen Polytechnic University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2798-3134","affiliations":[{"raw_affiliation_string":"Shenzhen Polytechnic University, Shenzhen, China","institution_ids":["https://openalex.org/I182722699"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005772506","display_name":"Chi\u2010Man Pun","orcid":"https://orcid.org/0000-0003-1788-3746"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chi Man Pun","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0003-1788-3746","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036370695","display_name":"Xuhang Chen","orcid":"https://orcid.org/0000-0001-6000-3914"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]},{"id":"https://openalex.org/I93477617","display_name":"Huizhou University","ror":"https://ror.org/03q3s7962","country_code":"CN","type":"education","lineage":["https://openalex.org/I93477617"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Xuhang Chen","raw_affiliation_strings":["Huizhou University, Huizhou, China and University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0001-6000-3914","affiliations":[{"raw_affiliation_string":"Huizhou University, Huizhou, China and University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544","https://openalex.org/I93477617"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.70179399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2561","last_page":"2570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.12110000103712082,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.12110000103712082,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11919999867677689,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.10490000247955322,"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/timbre","display_name":"Timbre","score":0.5947999954223633},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5608000159263611},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5164999961853027},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4629000127315521},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4311999976634979},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4099000096321106},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.3353999853134155},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757099986076355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6011000275611877},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5947999954223633},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38960000872612},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2780616401","wikidata":"https://www.wikidata.org/wiki/Q1133673","display_name":"Cornerstone","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C2775918612","wikidata":"https://www.wikidata.org/wiki/Q994794","display_name":"Noma","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C65165936","wikidata":"https://www.wikidata.org/wiki/Q575784","display_name":"Baseband","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810570","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810570","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810570","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810570","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5756368041038513,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2964243274","https://openalex.org/W2970641574","https://openalex.org/W3005287255","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210777104","https://openalex.org/W4224216673","https://openalex.org/W4285217427","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4381786045","https://openalex.org/W4382458974","https://openalex.org/W4382459088","https://openalex.org/W4386065718","https://openalex.org/W4392902843","https://openalex.org/W4392903711","https://openalex.org/W4392910544","https://openalex.org/W4395471131","https://openalex.org/W4399562496","https://openalex.org/W4402669230","https://openalex.org/W4402669711","https://openalex.org/W4402753815","https://openalex.org/W4402978614","https://openalex.org/W4403791273","https://openalex.org/W4405950485","https://openalex.org/W4406261673","https://openalex.org/W4406391458","https://openalex.org/W4408353269","https://openalex.org/W4409365102","https://openalex.org/W4412511526","https://openalex.org/W4412945617","https://openalex.org/W4415536237","https://openalex.org/W4415540902","https://openalex.org/W4415541148","https://openalex.org/W4416036921","https://openalex.org/W7087771355","https://openalex.org/W7124955536"],"related_works":[],"abstract_inverted_index":{"High-fidelity":[0],"character":[1],"voice":[2],"synthesis":[3],"is":[4,120],"a":[5,40,44,54,62,71,110],"cornerstone":[6],"of":[7],"immersive":[8],"multimedia":[9,115],"applications,":[10],"particularly":[11],"for":[12,113],"interacting":[13],"with":[14],"anime":[15],"avatars":[16],"and":[17,61,86,104],"digital":[18],"humans.":[19],"However,":[20],"existing":[21],"systems":[22],"struggle":[23],"to":[24],"maintain":[25],"consistent":[26],"persona":[27],"traits":[28],"across":[29],"diverse":[30],"emotional":[31,88],"contexts.":[32],"To":[33],"bridge":[34],"this":[35],"gap,":[36],"we":[37],"present":[38],"ATRIE,":[39],"unified":[41],"framework":[42],"utilizing":[43],"Persona-Prosody":[45],"Dual-Track":[46],"(P2-DT)":[47],"architecture.":[48],"Our":[49],"system":[50],"disentangles":[51],"generation":[52,103],"into":[53],"static":[55],"Timbre":[56],"Track":[57,65],"(via":[58,66],"Scalar":[59],"Quantization)":[60],"dynamic":[63],"Prosody":[64],"Hierarchical":[67],"Flow-Matching),":[68],"distilled":[69],"from":[70],"14B":[72],"LLM":[73],"teacher.":[74],"This":[75],"design":[76],"enables":[77],"robust":[78],"identity":[79],"preservation":[80],"(Zero-Shot":[81],"Speaker":[82],"Verification":[83],"EER:":[84],"0.04)":[85],"rich":[87],"expression.":[89],"Evaluated":[90],"on":[91],"our":[92],"extended":[93],"AnimeTTS-Bench":[94],"(50":[95],"characters),":[96],"ATRIE":[97],"achieves":[98],"state-of-the-art":[99],"performance":[100],"in":[101],"both":[102],"cross-modal":[105],"retrieval":[106],"(mAP:":[107],"0.75),":[108],"establishing":[109],"new":[111],"paradigm":[112],"persona-driven":[114],"content":[116],"creation.":[117],"The":[118],"code":[119],"available":[121],"at":[122],"Github.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-16T00:00:00"}
