{"id":"https://openalex.org/W4396542467","doi":"https://doi.org/10.1109/taslp.2024.3395994","title":"DiffProsody: Diffusion-Based Latent Prosody Generation for Expressive Speech Synthesis With Prosody Conditional Adversarial Training","display_name":"DiffProsody: Diffusion-Based Latent Prosody Generation for Expressive Speech Synthesis With Prosody Conditional Adversarial Training","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396542467","doi":"https://doi.org/10.1109/taslp.2024.3395994"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3395994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3395994","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5033088100","display_name":"Hyung-Seok Oh","orcid":"https://orcid.org/0000-0001-7229-8123"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung-Seok Oh","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-7229-8123","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033958396","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-8925-4474"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Software and Computer Engineering, Ajou University, Suwon-si, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8925-4474","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Ajou University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2013Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Software and Computer Engineering, Ajou University, Suwon-si, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6249-4996","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Ajou University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":4.6545,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95191133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2654","last_page":"2666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.9959999918937683,"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/prosody","display_name":"Prosody","score":0.9063937664031982},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5517563223838806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4724871516227722},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45371612906455994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4258178770542145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41045695543289185},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.39357826113700867}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9063937664031982},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5517563223838806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4724871516227722},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45371612906455994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4258178770542145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41045695543289185},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39357826113700867}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3395994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3395994","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2593414223","https://openalex.org/W2747874407","https://openalex.org/W2752796333","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2897353073","https://openalex.org/W2962788625","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2996414377","https://openalex.org/W3015440759","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W3150572638","https://openalex.org/W3158762648","https://openalex.org/W3163339651","https://openalex.org/W3168542456","https://openalex.org/W3202098869","https://openalex.org/W3202510435","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W3216941316","https://openalex.org/W4210433094","https://openalex.org/W4221159457","https://openalex.org/W4224035735","https://openalex.org/W4224926192","https://openalex.org/W4225320802","https://openalex.org/W4225892118","https://openalex.org/W4226050434","https://openalex.org/W4226332109","https://openalex.org/W4240592325","https://openalex.org/W4283771593","https://openalex.org/W4295036296","https://openalex.org/W4296068797","https://openalex.org/W4296068812","https://openalex.org/W4297841281","https://openalex.org/W4297841496","https://openalex.org/W4297841773","https://openalex.org/W4312933868","https://openalex.org/W4322616300","https://openalex.org/W4381786045","https://openalex.org/W4385823402","https://openalex.org/W4388333640","https://openalex.org/W4402905495","https://openalex.org/W6739901393","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6757817989","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790220310","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6802142237","https://openalex.org/W6809885388","https://openalex.org/W6811291704","https://openalex.org/W6838639034","https://openalex.org/W6838815585","https://openalex.org/W6850160943","https://openalex.org/W6853570719"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Expressive":[0],"text-to-speech":[1],"systems":[2],"have":[3,20],"undergone":[4],"significant":[5],"advancements":[6],"owing":[7],"to":[8,26,107],"prosody":[9,30,62,65,76,81,85,110,119],"modeling,":[10],"but":[11],"conventional":[12,125],"methods":[13],"can":[14],"still":[15],"be":[16],"improved.":[17],"Traditional":[18],"approaches":[19],"relied":[21],"on":[22],"the":[23,28,36,72,90,93,109,124],"autoregressive":[24],"method":[25,134],"predict":[27],"quantized":[29],"vector;":[31],"however,":[32],"it":[33],"suffers":[34],"from":[35],"issues":[37],"of":[38,74,92,117,131],"long-term":[39],"dependency":[40],"and":[41,64],"slow":[42],"inference.":[43],"This":[44],"study":[45],"proposes":[46],"a":[47,59,80],"novel":[48],"approach":[49],"called":[50],"DiffProsody":[51,114],"in":[52,78],"which":[53],"expressive":[54],"speech":[55,95],"is":[56,115],"synthesized":[57],"using":[58],"diffusion-based":[60],"latent":[61],"generator":[63,77],"conditional":[66,86],"adversarial":[67,105],"training.":[68],"Our":[69],"findings":[70],"confirm":[71],"effectiveness":[73],"our":[75,84,132],"generating":[79,118],"vector.":[82],"Furthermore,":[83],"discriminator":[87],"significantly":[88],"improves":[89],"quality":[91],"generated":[94],"by":[96],"accurately":[97],"emulating":[98],"prosody.":[99],"We":[100],"use":[101],"denoising":[102],"diffusion":[103,126],"generative":[104],"networks":[106],"improve":[108],"generation":[111],"speed.":[112],"Consequently,":[113],"capable":[116],"16":[120],"times":[121],"faster":[122],"than":[123],"model.":[127],"The":[128],"superior":[129],"performance":[130],"proposed":[133],"has":[135],"been":[136],"demonstrated":[137],"via":[138],"experiments.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}