{"id":"https://openalex.org/W4393372125","doi":"https://doi.org/10.1109/taslp.2024.3378110","title":"Controllable Accented Text-to-Speech Synthesis With Fine and Coarse-Grained Intensity Rendering","display_name":"Controllable Accented Text-to-Speech Synthesis With Fine and Coarse-Grained Intensity Rendering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393372125","doi":"https://doi.org/10.1109/taslp.2024.3378110"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3378110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3378110","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"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/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":"Rui Liu","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0003-4524-7413","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"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/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-8078-3305","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"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, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0005-5513-1192","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, 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/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","University of Bremen, Faculty 3 Computer Science / Mathematics, Enrique-Schmidt-Str. 5 Cartesium, Bremen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"University of Bremen, Faculty 3 Computer Science / Mathematics, Enrique-Schmidt-Str. 5 Cartesium, Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0012,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95716863,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2188","last_page":"2201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908999800682068,"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":0.9908999800682068,"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":0.9617999792098999,"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":0.9545000195503235,"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/rendering","display_name":"Rendering (computer graphics)","score":0.7587994337081909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5355019569396973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3912276327610016},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.31298691034317017}],"concepts":[{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7587994337081909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5355019569396973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3912276327610016},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.31298691034317017}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3378110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3378110","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":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G600008135","display_name":null,"funder_award_id":"62206136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":116,"referenced_works":["https://openalex.org/W8140679","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1877570817","https://openalex.org/W1965044932","https://openalex.org/W1985084205","https://openalex.org/W1991682319","https://openalex.org/W2000198779","https://openalex.org/W2015419244","https://openalex.org/W2017742648","https://openalex.org/W2020304287","https://openalex.org/W2085662862","https://openalex.org/W2091135796","https://openalex.org/W2091653553","https://openalex.org/W2091856355","https://openalex.org/W2124331435","https://openalex.org/W2133803203","https://openalex.org/W2133853764","https://openalex.org/W2135510989","https://openalex.org/W2139008940","https://openalex.org/W2150769028","https://openalex.org/W2169163929","https://openalex.org/W2191668891","https://openalex.org/W2295934277","https://openalex.org/W2395403337","https://openalex.org/W2398741870","https://openalex.org/W2402146185","https://openalex.org/W2402640444","https://openalex.org/W2514457011","https://openalex.org/W2552635739","https://openalex.org/W2749298174","https://openalex.org/W2888954148","https://openalex.org/W2890402938","https://openalex.org/W2903739847","https://openalex.org/W2938359332","https://openalex.org/W2954386831","https://openalex.org/W2955237921","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972473628","https://openalex.org/W2973142754","https://openalex.org/W2978690368","https://openalex.org/W2983786745","https://openalex.org/W2994735258","https://openalex.org/W2997540646","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3015430779","https://openalex.org/W3015915933","https://openalex.org/W3016021263","https://openalex.org/W3092028330","https://openalex.org/W3095545636","https://openalex.org/W3096894480","https://openalex.org/W3127424476","https://openalex.org/W3135654121","https://openalex.org/W3150572638","https://openalex.org/W3160255128","https://openalex.org/W3162770051","https://openalex.org/W3168542456","https://openalex.org/W3174285493","https://openalex.org/W3178546316","https://openalex.org/W3196543367","https://openalex.org/W3197541421","https://openalex.org/W3197558340","https://openalex.org/W3197742413","https://openalex.org/W3198104520","https://openalex.org/W3202098869","https://openalex.org/W3204009030","https://openalex.org/W4200629210","https://openalex.org/W4224926192","https://openalex.org/W4240592325","https://openalex.org/W4247617301","https://openalex.org/W4283009359","https://openalex.org/W4283397032","https://openalex.org/W4285483692","https://openalex.org/W4296068424","https://openalex.org/W4297841867","https://openalex.org/W4308614654","https://openalex.org/W4312356750","https://openalex.org/W4319781852","https://openalex.org/W4319862665","https://openalex.org/W4366493008","https://openalex.org/W4367032484","https://openalex.org/W4383220533","https://openalex.org/W4385245566","https://openalex.org/W4385807417","https://openalex.org/W4385822302","https://openalex.org/W4385822358","https://openalex.org/W4385822470","https://openalex.org/W4385822994","https://openalex.org/W4385823392","https://openalex.org/W4385823473","https://openalex.org/W4391892546","https://openalex.org/W6631190155","https://openalex.org/W6683276001","https://openalex.org/W6696992736","https://openalex.org/W6730349644","https://openalex.org/W6734815144","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6756197946","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6771024825","https://openalex.org/W6771977774","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6795807602","https://openalex.org/W6796093936","https://openalex.org/W6840040786","https://openalex.org/W6847740417","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W291250033","https://openalex.org/W2035757446","https://openalex.org/W2008385118","https://openalex.org/W880955280","https://openalex.org/W2106647072","https://openalex.org/W4246858109","https://openalex.org/W2172753644","https://openalex.org/W54172855","https://openalex.org/W2170209930","https://openalex.org/W2046782623"],"abstract_inverted_index":{"Accented":[0,43],"text-to-speech":[1],"(TTS)":[2],"synthesis":[3],"seeks":[4,202],"to":[5,85,89,136,160,180,203,258],"generate":[6],"speech":[7,93,172,237],"with":[8,216,281],"an":[9,65,109,170],"accent":[10,75,106,139,156,163,176,183,222,241,265],"(L2)":[11],"as":[12,23,51],"a":[13,129,195,213,228],"variant":[14],"of":[15,31,68,77,104,165,219,264,278],"the":[16,74,83,102,105,138,152,162,182,193,205,217,220,226,234,239,246,252,259,275],"standard":[17],"version":[18],"(L1),":[19],"which":[20],"is":[21,25,97,145,243,274],"challenging":[22],"L2":[24,187,236],"different":[26],"from":[27],"L1":[28],"in":[29,185,245,262],"terms":[30,263],"phonetic":[32],"rendering":[33,266],"and":[34,39,55,59,70,114,120,141,154,168,189,209,267,288],"prosody":[35],"pattern":[36],"(pitch,":[37],"energy,":[38],"duration":[40,210],"variance,":[41],"etc.).":[42],"TTS":[44,131,166,280],"has":[45,82],"several":[46],"significant":[47],"real-world":[48],"applications,":[49],"such":[50],"language":[52],"learning,":[53],"preserving":[54],"documenting":[56],"endangered":[57],"languages":[58],"dialects,":[60],"etc.":[61],"that":[62,117,133,232,251],"make":[63],"it":[64],"important":[66],"area":[67],"research":[69],"development.":[71],"Moreover,":[72],"changing":[73],"intensity":[76,107,177,184,223,268,283],"any":[78],"conversational":[79],"AI":[80],"system":[81,254],"potential":[84],"allow":[86],"specific":[87],"users":[88],"understand":[90],"its":[91,142],"produced":[92],"better.":[94],"However,":[95],"there":[96],"no":[98],"intuitive":[99],"solution":[100],"for":[101,108],"control":[103,137,284],"utterance":[110,121,190],"at":[111,212,285],"both":[112,186,286],"fine":[113,287],"coarse-grained":[115,289],"levels,":[116],"are":[118],"phoneme":[119,188,214],"levels":[122],"respectively.":[123],"In":[124,192,225],"this":[125,273],"work,":[126],"we":[127],"propose":[128],"neural":[130],"architecture":[132],"allows":[134],"us":[135],"style":[140],"intensity.":[143],"This":[144],"achieved":[146],"through":[147],"two":[148],"novel":[149],"mechanisms:":[150],"1)":[151],"front-end":[153],"back-end":[155],"knowledge":[157],"injection":[158],"mechanism":[159],"enhance":[161],"interpretability":[164],"modeling;":[167],"2)":[169],"automatic":[171],"recognition":[173],"(ASR)":[174],"based":[175],"modeling":[178],"strategy":[179],"quantify":[181],"levels.":[191,290],"front-end,":[194,247],"new":[196],"<italic":[197],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">accent":[199],"variation":[200],"adaptor</i>":[201],"project":[204],"accent-aware":[206],"pitch,":[207],"energy":[208],"features":[211],"level,":[215],"help":[218],"fine-grained":[221],"information;":[224],"back-end,":[227],"consistency":[229],"constraint":[230],"module":[231],"ensures":[233],"synthesized":[235],"manifests":[238],"expected":[240],"intensity,":[242],"injected":[244],"precisely.":[248],"Experiments":[249],"show":[250],"proposed":[253],"attains":[255],"superior":[256],"performance":[257],"baseline":[260],"models":[261],"control.":[269],"To":[270],"our":[271],"knowledge,":[272],"first":[276],"study":[277],"accented":[279],"explicit":[282]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}