{"id":"https://openalex.org/W4375869364","doi":"https://doi.org/10.1109/icassp49357.2023.10095621","title":"Emodiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance","display_name":"Emodiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869364","doi":"https://doi.org/10.1109/icassp49357.2023.10095621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101579214","display_name":"Yiwei Guo","orcid":"https://orcid.org/0009-0003-8114-2085"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0009-0004-4458-0753"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101579214"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.8662,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96067015,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7619487047195435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6341278553009033},{"id":"https://openalex.org/keywords/intensity","display_name":"Intensity (physics)","score":0.5376402735710144},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49362218379974365},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4672052264213562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4598873555660248},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4491196274757385},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4275321066379547},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4150053560733795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619487047195435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6341278553009033},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.5376402735710144},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49362218379974365},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4672052264213562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4598873555660248},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4491196274757385},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4275321066379547},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4150053560733795},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":49,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2294130536","https://openalex.org/W2770743791","https://openalex.org/W2959300817","https://openalex.org/W3008691130","https://openalex.org/W3015841875","https://openalex.org/W3016021263","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3110257065","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3136699727","https://openalex.org/W3146550708","https://openalex.org/W3158762648","https://openalex.org/W3162926177","https://openalex.org/W3163573274","https://openalex.org/W3169905056","https://openalex.org/W3172148458","https://openalex.org/W3193748859","https://openalex.org/W3198123658","https://openalex.org/W3198213150","https://openalex.org/W3216941316","https://openalex.org/W4200634729","https://openalex.org/W4210777104","https://openalex.org/W4221147462","https://openalex.org/W4221167022","https://openalex.org/W4224926192","https://openalex.org/W4226132755","https://openalex.org/W4226213470","https://openalex.org/W4285605725","https://openalex.org/W4313316128","https://openalex.org/W4320169845","https://openalex.org/W6631362777","https://openalex.org/W6746238782","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6795288823","https://openalex.org/W6796464841","https://openalex.org/W6804423701","https://openalex.org/W6805282115","https://openalex.org/W6810360501","https://openalex.org/W6811008979","https://openalex.org/W6849953009"],"related_works":["https://openalex.org/W2031481447","https://openalex.org/W2216757598","https://openalex.org/W3013209356","https://openalex.org/W4387496629","https://openalex.org/W2092201493","https://openalex.org/W2489800615","https://openalex.org/W2356089377","https://openalex.org/W2799713421","https://openalex.org/W2382505436","https://openalex.org/W2102737569"],"abstract_inverted_index":{"Although":[0],"current":[1],"neural":[2],"text-to-speech":[3],"(TTS)":[4],"models":[5],"are":[6],"able":[7],"to":[8,31,94,114],"generate":[9],"high-quality":[10],"speech,":[11],"intensity":[12,28,49,107,126,138],"controllable":[13],"emotional":[14],"TTS":[15,45],"is":[16,77,92],"still":[17],"a":[18,43,54,69,80],"challenging":[19],"task.":[20],"Most":[21],"existing":[22],"methods":[23],"need":[24],"external":[25],"optimizations":[26],"for":[27,72],"calculation,":[29],"leading":[30],"suboptimal":[32],"results":[33],"or":[34],"degraded":[35],"quality.":[36,131],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"EmoDiff,":[42],"diffusion-based":[44],"model":[46],"where":[47,83],"emotion":[48,89,106,125,137],"can":[50,109,121,139],"be":[51,110,140],"manipulated":[52],"by":[53,142],"proposed":[55],"soft-label":[56],"guidance":[57],"technique":[58],"derived":[59],"from":[60,112],"classifier":[61],"guidance.":[62],"Specifically,":[63],"instead":[64],"of":[65,86],"being":[66],"guided":[67,78],"with":[68,79,135],"one-hot":[70],"vector":[71],"the":[73,84,87,105,124,145],"specified":[74,88,136],"emotion,":[75],"EmoDiff":[76,120],"soft":[81],"label":[82],"value":[85],"and":[90,96,108],"Neutral":[91],"set":[93],"\u03b1":[95,99,102],"1":[97],"\u2212":[98],"respectively.":[100],"The":[101],"here":[103],"represents":[104],"chosen":[111],"0":[113],"1.":[115],"Our":[116],"experiments":[117],"show":[118],"that":[119],"precisely":[122],"control":[123],"while":[127],"maintaining":[128],"high":[129],"voice":[130],"Moreover,":[132],"diverse":[133],"speech":[134],"generated":[141],"sampling":[143],"in":[144],"reverse":[146],"denoising":[147],"process.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
