{"id":"https://openalex.org/W4408354026","doi":"https://doi.org/10.1109/icassp49660.2025.10888978","title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","display_name":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354026","doi":"https://doi.org/10.1109/icassp49660.2025.10888978"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5101414146","display_name":"Xin Jing","orcid":"https://orcid.org/0000-0002-3425-3968"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xin Jing","raw_affiliation_strings":["Technical University of Munich,CHI &#x2013; Chair of Health Informatics,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI &#x2013; Chair of Health Informatics,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654458","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0002-7869-4474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Alibaba Group,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Triantafyllopoulos","raw_affiliation_strings":["Technical University of Munich,CHI &#x2013; Chair of Health Informatics,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI &#x2013; Chair of Health Informatics,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Technical University of Munich,CHI &#x2013; Chair of Health Informatics,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI &#x2013; Chair of Health Informatics,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.6527000069618225,"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":0.6527000069618225,"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/T12031","display_name":"Speech and dialogue systems","score":0.5963000059127808,"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/controllability","display_name":"Controllability","score":0.7978004217147827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523446679115295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.58133465051651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.53269362449646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5192939639091492},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4955793619155884},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4875633120536804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07109075784683228}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.7978004217147827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523446679115295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.58133465051651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53269362449646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5192939639091492},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4955793619155884},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4875633120536804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07109075784683228},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2029349470","https://openalex.org/W2085662862","https://openalex.org/W2239141610","https://openalex.org/W2742542661","https://openalex.org/W3142644187","https://openalex.org/W3163573274","https://openalex.org/W4205742757","https://openalex.org/W4221147462","https://openalex.org/W4250328251","https://openalex.org/W4254718357","https://openalex.org/W4313316128","https://openalex.org/W4317514614","https://openalex.org/W4323896824","https://openalex.org/W4360884927","https://openalex.org/W4361994820","https://openalex.org/W4372259784","https://openalex.org/W4372263438","https://openalex.org/W4375869257","https://openalex.org/W4380434618","https://openalex.org/W4385570943","https://openalex.org/W4385822787","https://openalex.org/W4385823160","https://openalex.org/W4391280467","https://openalex.org/W4392904615","https://openalex.org/W4396877837","https://openalex.org/W4398152753","https://openalex.org/W4400234937","https://openalex.org/W4400615667","https://openalex.org/W4402111427","https://openalex.org/W4402111518","https://openalex.org/W6755207826","https://openalex.org/W6786375611","https://openalex.org/W6791353385","https://openalex.org/W6796464841","https://openalex.org/W6809885388","https://openalex.org/W6849416043","https://openalex.org/W6850607732","https://openalex.org/W6856828098","https://openalex.org/W6865532752"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2140812588","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"While":[0],"current":[1],"emotional":[2,10,35,49,75,80],"text-to-speech":[3],"(TTS)":[4],"systems":[5],"can":[6],"generate":[7,74],"highly":[8],"intelligible":[9],"speech,":[11],"achieving":[12],"fine":[13],"control":[14,47,129],"over":[15,48],"emotion":[16,130],"rendering":[17,131],"of":[18,42],"the":[19,40,68,91],"output":[20],"speech":[21,109,134],"still":[22],"remains":[23],"a":[24,33,53,59,96],"significant":[25],"challenge.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"introduce":[31],"ParaEVITS,":[32],"novel":[34],"TTS":[36],"framework":[37,84],"that":[38,126],"leverages":[39],"compositionality":[41],"natural":[43],"language":[44],"to":[45,73,99],"enhance":[46],"rendering.":[50],"By":[51],"incorporating":[52],"text-audio":[54],"encoder":[55],"inspired":[56],"by":[57],"ParaCLAP,":[58],"contrastive":[60],"language-audio":[61],"pretraining":[62],"(CLAP)":[63],"model":[64,70,98],"for":[65],"computational":[66],"paralinguistics,":[67],"diffusion":[69,97],"is":[71],"trained":[72],"embeddings":[76],"based":[77],"on":[78,87],"textual":[79,101,121],"style":[81],"descriptions.":[82],"Our":[83,123],"first":[85],"trains":[86],"reference":[88],"audio":[89,92],"using":[90,119],"encoder,":[93],"then":[94],"fine-tunes":[95],"process":[100],"inputs":[102],"from":[103],"ParaCLAP\u2019s":[104],"text":[105],"encoder.":[106],"During":[107],"inference,":[108],"attributes":[110],"such":[111],"as":[112],"pitch,":[113],"jitter,":[114],"and":[115],"loudness":[116],"are":[117,138],"manipulated":[118],"only":[120],"conditioning.":[122],"experiments":[124],"demonstrate":[125],"ParaEVITS":[127],"effectively":[128],"without":[132],"compromising":[133],"quality.":[135],"Speech":[136],"demos":[137],"publicly":[139],"available<sup":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}