{"id":"https://openalex.org/W4372340836","doi":"https://doi.org/10.1109/icassp49357.2023.10097118","title":"Fine-Grained Emotional Control of Text-to-Speech: Learning to Rank Inter- and Intra-Class Emotion Intensities","display_name":"Fine-Grained Emotional Control of Text-to-Speech: Learning to Rank Inter- and Intra-Class Emotion Intensities","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372340836","doi":"https://doi.org/10.1109/icassp49357.2023.10097118"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097118","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":"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/A5100627209","display_name":"Shijun Wang","orcid":"https://orcid.org/0000-0001-7290-412X"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shijun Wang","raw_affiliation_strings":["University of St.Gallen,Switzerland","University of St.Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St.Gallen,Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]},{"raw_affiliation_string":"University of St.Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079762083","display_name":"J\u00f3n Gu\u00f0nason","orcid":"https://orcid.org/0000-0001-6560-5543"},"institutions":[{"id":"https://openalex.org/I123185442","display_name":"Reykjav\u00edk University","ror":"https://ror.org/05d2kyx68","country_code":"IS","type":"education","lineage":["https://openalex.org/I123185442"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"J\u00f3n Gu\u00f0nason","raw_affiliation_strings":["Reykjavik University,Iceland","Reykjavik University, Iceland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reykjavik University,Iceland","institution_ids":["https://openalex.org/I123185442"]},{"raw_affiliation_string":"Reykjavik University, Iceland","institution_ids":["https://openalex.org/I123185442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Damian Borth","raw_affiliation_strings":["University of St.Gallen,Switzerland","University of St.Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of St.Gallen,Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]},{"raw_affiliation_string":"University of St.Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9965999722480774,"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/naturalness","display_name":"Naturalness","score":0.8364804983139038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245333194732666},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.7190465927124023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.614869236946106},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5892905592918396},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5468912720680237},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5355373024940491},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5061530470848083},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.43223798274993896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35371875762939453},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3294471204280853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1121605932712555}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8364804983139038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245333194732666},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.7190465927124023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.614869236946106},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5892905592918396},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5468912720680237},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5355373024940491},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5061530470848083},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.43223798274993896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35371875762939453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3294471204280853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1121605932712555},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097118","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":26,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2747874407","https://openalex.org/W2765407302","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2810914326","https://openalex.org/W2901997113","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W3008691130","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3126404598","https://openalex.org/W3146550708","https://openalex.org/W3174758275","https://openalex.org/W3196543367","https://openalex.org/W3198843334","https://openalex.org/W4210777104","https://openalex.org/W4312732823","https://openalex.org/W6745136726","https://openalex.org/W6746238782","https://openalex.org/W6750489868","https://openalex.org/W6753049143","https://openalex.org/W6756197946","https://openalex.org/W6790138166","https://openalex.org/W6911026449"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250"],"abstract_inverted_index":{"State-of-the-art":[0],"Text-To-Speech":[1],"(TTS)":[2],"models":[3,39,110],"are":[4,45,66],"capable":[5],"of":[6,29,60],"producing":[7],"high-quality":[8],"speech.":[9],"The":[10],"generated":[11],"speech,":[12],"however,":[13],"is":[14],"usually":[15],"neutral":[16],"in":[17],"emotional":[18,27,77],"expression,":[19],"whereas":[20],"very":[21],"often":[22,67],"one":[23],"would":[24],"want":[25],"fine-grained":[26,75],"control":[28,48],"words":[30],"or":[31],"phonemes.":[32],"Although":[33],"still":[34],"challenging,":[35],"the":[36,58,63],"first":[37],"TTS":[38,109],"have":[40],"been":[41],"recently":[42],"proposed":[43],"that":[44,79,102],"able":[46,88],"to":[47,57,89],"voice":[49],"by":[50],"manually":[51],"assigning":[52],"emotion":[53,113],"intensity.":[54],"Unfortunately,":[55],"due":[56],"neglect":[59],"intra-class":[61,84],"distance,":[62],"intensity":[64,94],"differences":[65],"unrecognizable.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"a":[74],"controllable":[76,108],"TTS,":[78],"considers":[80],"both":[81],"inter-":[82],"and":[83,86,98,115],"distances":[85],"be":[87],"synthesize":[90],"speech":[91],"with":[92],"recognizable":[93],"difference.":[95],"Our":[96],"subjective":[97],"objective":[99],"experiments":[100],"demonstrate":[101],"our":[103],"model":[104],"exceeds":[105],"two":[106],"state-of-the-art":[107],"for":[111],"controllability,":[112],"expressiveness":[114],"naturalness.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
