{"id":"https://openalex.org/W3168542456","doi":"https://doi.org/10.1109/taslp.2021.3076369","title":"Expressive TTS Training With Frame and Style Reconstruction Loss","display_name":"Expressive TTS Training With Frame and Style Reconstruction Loss","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3168542456","doi":"https://doi.org/10.1109/taslp.2021.3076369","mag":"3168542456"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3076369","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3076369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2021.3076369","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Singapore University of Technology and Design (SUTD) and National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design (SUTD) and National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399","https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["Singapore University of Technology and Design (SUTD), Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design (SUTD), Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Huhhot, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["DE","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore","Faculty 3 Computer Science/Mathematics, Enrique-Schmidt-Str. 5 Cartesium, University of Bremen, Bremen, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Faculty 3 Computer Science/Mathematics, Enrique-Schmidt-Str. 5 Cartesium, University of Bremen, Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082746577"],"corresponding_institution_ids":["https://openalex.org/I152815399","https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":8.2939,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98023343,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"1806","last_page":"1818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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":0.996399998664856,"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/style","display_name":"Style (visual arts)","score":0.6938642263412476},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6723755598068237},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6329246759414673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4807857871055603},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3626709282398224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32428744435310364},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1550503373146057},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10124263167381287},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.09910976886749268},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06974172592163086},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06282570958137512}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6938642263412476},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6723755598068237},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6329246759414673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4807857871055603},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3626709282398224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32428744435310364},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1550503373146057},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10124263167381287},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.09910976886749268},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06974172592163086},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06282570958137512},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3076369","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3076369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/taslp.2021.3076369","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3076369","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G1094757534","display_name":null,"funder_award_id":"AISG-GC-2019-002","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3191157935","display_name":null,"funder_award_id":"AISG-100E-2018-006","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":140,"referenced_works":["https://openalex.org/W39968598","https://openalex.org/W113106864","https://openalex.org/W162654330","https://openalex.org/W188951208","https://openalex.org/W251642908","https://openalex.org/W344150399","https://openalex.org/W397522103","https://openalex.org/W1540083112","https://openalex.org/W1552314771","https://openalex.org/W1581458799","https://openalex.org/W1606487971","https://openalex.org/W1689711448","https://openalex.org/W1836465849","https://openalex.org/W1959608418","https://openalex.org/W1969386661","https://openalex.org/W1973378890","https://openalex.org/W2025617415","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2123237149","https://openalex.org/W2127589467","https://openalex.org/W2145577652","https://openalex.org/W2146334809","https://openalex.org/W2150658333","https://openalex.org/W2156146072","https://openalex.org/W2163605009","https://openalex.org/W2187089797","https://openalex.org/W2195693064","https://openalex.org/W2330979245","https://openalex.org/W2331128040","https://openalex.org/W2395980997","https://openalex.org/W2404839462","https://openalex.org/W2517513811","https://openalex.org/W2519091744","https://openalex.org/W2529497146","https://openalex.org/W2558531213","https://openalex.org/W2600829178","https://openalex.org/W2604184139","https://openalex.org/W2618530766","https://openalex.org/W2714549561","https://openalex.org/W2740504963","https://openalex.org/W2748654097","https://openalex.org/W2759925408","https://openalex.org/W2766272105","https://openalex.org/W2769810959","https://openalex.org/W2785978752","https://openalex.org/W2786387703","https://openalex.org/W2786868129","https://openalex.org/W2790783922","https://openalex.org/W2791322592","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2798951647","https://openalex.org/W2804664105","https://openalex.org/W2885005742","https://openalex.org/W2885800352","https://openalex.org/W2888932932","https://openalex.org/W2889028433","https://openalex.org/W2889064624","https://openalex.org/W2911340057","https://openalex.org/W2937154351","https://openalex.org/W2941094131","https://openalex.org/W2945544731","https://openalex.org/W2949973225","https://openalex.org/W2952269766","https://openalex.org/W2963087613","https://openalex.org/W2963174698","https://openalex.org/W2963272440","https://openalex.org/W2963522749","https://openalex.org/W2963782041","https://openalex.org/W2963927338","https://openalex.org/W2963945466","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972394484","https://openalex.org/W2972443522","https://openalex.org/W2972595148","https://openalex.org/W2972702018","https://openalex.org/W2972789651","https://openalex.org/W2973013313","https://openalex.org/W2982037672","https://openalex.org/W3010916717","https://openalex.org/W3012016043","https://openalex.org/W3012404734","https://openalex.org/W3015440759","https://openalex.org/W3015841875","https://openalex.org/W3016021263","https://openalex.org/W3016027511","https://openalex.org/W3016050488","https://openalex.org/W3016151052","https://openalex.org/W3019993940","https://openalex.org/W3025182306","https://openalex.org/W3026278778","https://openalex.org/W3094124570","https://openalex.org/W3094917204","https://openalex.org/W3096086473","https://openalex.org/W3096830101","https://openalex.org/W3098557217","https://openalex.org/W3102739662","https://openalex.org/W3106690208","https://openalex.org/W3154443551","https://openalex.org/W3162271107","https://openalex.org/W3163573274","https://openalex.org/W4240592325","https://openalex.org/W4294619240","https://openalex.org/W4295731579","https://openalex.org/W4297800839","https://openalex.org/W4298580827","https://openalex.org/W4390911378","https://openalex.org/W6601608730","https://openalex.org/W6604530167","https://openalex.org/W6606697926","https://openalex.org/W6607761755","https://openalex.org/W6611766843","https://openalex.org/W6634507583","https://openalex.org/W6636045042","https://openalex.org/W6638667902","https://openalex.org/W6640963894","https://openalex.org/W6675380101","https://openalex.org/W6678292227","https://openalex.org/W6678929712","https://openalex.org/W6681857489","https://openalex.org/W6692550842","https://openalex.org/W6712034360","https://openalex.org/W6728214246","https://openalex.org/W6736010183","https://openalex.org/W6736356763","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6761673384","https://openalex.org/W6762643587","https://openalex.org/W6777567901","https://openalex.org/W6778385928","https://openalex.org/W6784342092","https://openalex.org/W6784688130","https://openalex.org/W6860575079","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2356229341","https://openalex.org/W3216976533","https://openalex.org/W100620283"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,68,75,88,95,142,194],"novel":[3],"training":[4,45,163,199],"strategy":[5,164],"for":[6,200],"Tacotron-based":[7,69],"text-to-speech":[8],"(TTS)":[9],"system":[10],"that":[11,32,106,122,147,160],"improves":[12],"the":[13,21,28,58,78,110,126,161,170,184],"speech":[14,150],"styling":[15],"at":[16],"utterance":[17,117,148,189],"level.":[18],"One":[19],"of":[20,30,90,97,130],"key":[22],"challenges":[23],"in":[24,173],"prosody":[25,42,52,65,83,91],"modeling":[26,35],"is":[27,84,107,123,139,152,183],"lack":[29],"reference":[31],"makes":[33],"explicit":[34],"difficult.":[36],"The":[37,135],"proposed":[38,162],"technique":[39],"doesn\u2019t":[40,48],"require":[41],"annotations":[43],"from":[44,77],"data.":[46],"It":[47,93],"attempt":[49],"to":[50,145,187],"model":[51],"explicitly":[53,85],"either,":[54],"but":[55],"rather":[56],"encodes":[57],"association":[59],"between":[60,109,125],"input":[61],"text":[62],"and":[63,112,132,168,176],"its":[64],"styles":[66],"using":[67],"TTS":[70],"framework.":[71],"This":[72],"study":[73,186],"marks":[74],"departure":[76],"style":[79,119,128,136,151],"token":[80],"paradigm":[81],"where":[82],"modeled":[86],"by":[87],"bank":[89],"embeddings.":[92],"adopts":[94],"combination":[96],"two":[98],"objective":[99],"functions:":[100],"1)":[101],"frame":[102],"level":[103,118,149,190],"reconstruction":[104,120,137],"loss,":[105,121],"calculated":[108,124],"synthesized":[111,131],"target":[113,133],"spectral":[114],"features;":[115],"2)":[116],"deep":[127],"features":[129],"speech.":[134],"loss":[138,144,195],"formulated":[140],"as":[141,193],"perceptual":[143,191],"ensure":[146],"taken":[153],"into":[154,197],"consideration":[155],"during":[156],"training.":[157],"Experiments":[158],"show":[159],"achieves":[165],"remarkable":[166],"performance":[167],"outperforms":[169],"state-of-the-art":[171],"baseline":[172],"both":[174],"naturalness":[175],"expressiveness.":[177,202],"To":[178],"our":[179],"best":[180],"knowledge,":[181],"this":[182],"first":[185],"incorporate":[188],"quality":[192],"function":[196],"Tacotron":[198],"improved":[201]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}