{"id":"https://openalex.org/W7125894093","doi":"https://doi.org/10.1109/smc58881.2025.11342604","title":"Emotional Speech Synthesis via Diffusion Transformer with Reference Audio Pool <sup>*</sup>","display_name":"Emotional Speech Synthesis via Diffusion Transformer with Reference Audio Pool <sup>*</sup>","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125894093","doi":"https://doi.org/10.1109/smc58881.2025.11342604"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"article","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/A5124065252","display_name":"Qian Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Shen","raw_affiliation_strings":["Yunnan University,School of Information Science &amp; Engineering,Kunming,China,650500"],"affiliations":[{"raw_affiliation_string":"Yunnan University,School of Information Science &amp; Engineering,Kunming,China,650500","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404947","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-4801-7162"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Yunnan University,School of Information Science &amp; Engineering,Kunming,China,650500"],"affiliations":[{"raw_affiliation_string":"Yunnan University,School of Information Science &amp; Engineering,Kunming,China,650500","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124065252"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87110579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1888","last_page":"1893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7519000172615051,"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":0.7519000172615051,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.09679999947547913,"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/T11448","display_name":"Face recognition and analysis","score":0.022600000724196434,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8274000287055969},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.58160001039505},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5249999761581421},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5246999859809875},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8274000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640999913215637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6159999966621399},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.58160001039505},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C3020774634","wikidata":"https://www.wikidata.org/wiki/Q3113318","display_name":"Emotional valence","level":3,"score":0.2711000144481659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W3015282541","https://openalex.org/W3015338123","https://openalex.org/W3135644023","https://openalex.org/W3196308991","https://openalex.org/W3198123658","https://openalex.org/W3198213150","https://openalex.org/W4304099317","https://openalex.org/W4313316128","https://openalex.org/W4372260261","https://openalex.org/W4385823163","https://openalex.org/W4387968164","https://openalex.org/W4390872297","https://openalex.org/W4391020683"],"related_works":[],"abstract_inverted_index":{"Emotional":[0],"Speech":[1],"Synthesis":[2],"(ESS)":[3],"is":[4],"valuable":[5],"in":[6,21],"emotional":[7,22,35,41,63,83,93,124,136,155],"human-computer":[8],"interaction,":[9],"virtual":[10],"assistants,":[11],"and":[12,24,32,103,116,126,134,154],"media":[13],"dubbing.":[14],"However,":[15],"current":[16],"methodologies":[17],"face":[18],"persistent":[19],"challenges":[20],"diversity":[23,31],"acoustic":[25],"granularity.":[26],"To":[27],"effectively":[28],"enhance":[29,108],"the":[30,47,78,87,113,141,146,158,161],"subtlety":[33],"of":[34,89,123,132,160],"expression,":[36],"this":[37],"paper":[38],"proposes":[39],"an":[40,62],"speech":[42,67,137,151],"synthesis":[43,68,138,152],"method":[44],"based":[45,69,139],"on":[46,70,92,140],"Diffusion":[48,100],"Transformer":[49,101],"(DiT)":[50],"architecture":[51],"with":[52,98],"reference":[53,72,79],"audio":[54,73,80],"pool.":[55,74],"The":[56,129],"main":[57],"contributions":[58],"include:":[59],"(1)":[60],"Designing":[61],"modeling":[64],"strategy":[65],"for":[66,120],"a":[71,99],"By":[75],"randomly":[76],"sampling":[77],"corresponding":[81],"to":[82,107],"categories,":[84],"it":[85],"overcomes":[86],"limitation":[88],"single-reference":[90],"constraints":[91],"diversity;":[94],"(2)":[95],"Replacing":[96],"U-Net":[97],"backbone":[102],"using":[104],"overlapping":[105],"patches":[106],"local":[109],"details;":[110],"(3)":[111],"Introducing":[112],"style":[114,117],"encoder":[115],"adapter":[118],"modules":[119],"cross-attention-based":[121],"blending":[122],"features":[125],"text":[127],"embeddings.":[128],"experimental":[130],"results":[131],"Chinese":[133],"English":[135],"ESD":[142],"dataset":[143],"show":[144],"that":[145],"proposed":[147],"model":[148],"achieves":[149],"higher":[150],"naturalness":[153],"similarity,":[156],"verifying":[157],"effectiveness":[159],"method.":[162]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}