{"id":"https://openalex.org/W4405633932","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800372","title":"Learning Contrastive Emotional Nuances in Speech Synthesis","display_name":"Learning Contrastive Emotional Nuances in Speech Synthesis","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633932","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800372"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Bryan Gautama Ngo","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bryan Gautama Ngo","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043243811","display_name":"Mahdin Rohmatillah","orcid":"https://orcid.org/0000-0001-8417-2165"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mahdin Rohmatillah","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7563999891281128,"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/T12031","display_name":"Speech and dialogue systems","score":0.7563999891281128,"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":0.6700000166893005,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.6312000155448914,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6266879439353943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4603642225265503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4080883264541626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.40775662660598755},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3464236259460449},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05642354488372803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6266879439353943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4603642225265503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4080883264541626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40775662660598755},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3464236259460449},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05642354488372803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2747874407","https://openalex.org/W2760103357","https://openalex.org/W2904459034","https://openalex.org/W3097290232","https://openalex.org/W3116256056","https://openalex.org/W3163573274","https://openalex.org/W3196475561","https://openalex.org/W3197034238","https://openalex.org/W4224926192","https://openalex.org/W4247726808","https://openalex.org/W4286747238","https://openalex.org/W4297841867","https://openalex.org/W4313316128","https://openalex.org/W4319585922","https://openalex.org/W4375869257","https://openalex.org/W4385822470","https://openalex.org/W4385823060","https://openalex.org/W4391021646","https://openalex.org/W4392903682","https://openalex.org/W4396982391","https://openalex.org/W4400905918","https://openalex.org/W6675409298","https://openalex.org/W6750489868","https://openalex.org/W6778083308"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Prosody":[0],"is":[1],"a":[2,61,105,122],"crucial":[3],"speech":[4,115],"feature":[5],"in":[6,21,29,42,95,108],"emotional":[7,22,40,96,129],"text":[8],"-":[9],"to-speech":[10],"(TTS),":[11],"as":[12],"different":[13,78],"emotions":[14],"have":[15,24],"distinct":[16],"prosodic":[17],"characteristics.":[18],"Existing":[19],"works":[20],"TTS":[23,102],"primarily":[25],"utilized":[26],"emotion":[27,35,55,68,91,107],"labels":[28,69,92],"the":[30,43,52,72,85,90,100,132,135],"dataset":[31],"by":[32],"applying":[33],"auxiliary":[34],"classification":[36],"loss":[37],"to":[38,65,74],"enhance":[39],"nuances":[41],"model.":[44],"However,":[45],"this":[46,58,81],"approach":[47,64],"may":[48],"only":[49],"partially":[50],"leverage":[51],"potential":[53],"of":[54,134],"labels.":[56],"Accordingly,":[57],"paper":[59],"proposes":[60],"supervised":[62],"contrastive":[63,87],"effectively":[66],"utilize":[67],"and":[70],"enable":[71],"model":[73],"distinguish":[75],"prosody":[76,120],"from":[77,121],"emotions.":[79],"Furthermore,":[80],"work":[82],"also":[83],"explores":[84],"unsupervised":[86],"learning":[88],"where":[89],"are":[93],"missing":[94],"TTS.":[97],"In":[98],"particular,":[99],"proposed":[101,136],"architecture":[103],"assures":[104],"cross-speaker":[106],"transfer":[109],"learning,":[110],"allowing":[111],"for":[112],"an":[113],"accurate":[114],"generation":[116],"even":[117],"without":[118],"specific":[119],"target":[123],"speaker.":[124],"The":[125],"experimental":[126],"results":[127],"on":[128],"datasets":[130],"demonstrate":[131],"effectiveness":[133],"method.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}