{"id":"https://openalex.org/W7148363542","doi":"https://doi.org/10.1109/asru65441.2025.11434737","title":"Scalable Controllable Accented TTS","display_name":"Scalable Controllable Accented TTS","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148363542","doi":"https://doi.org/10.1109/asru65441.2025.11434737"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-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/A5024403590","display_name":"Henry Li Xinyuan","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Henry Li Xinyuan","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076833848","display_name":"Zexin Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zexin Cai","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715082","display_name":"Ashi Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashi Garg","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Duh","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garc\u00eda-Perera","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111560316","display_name":"Nicholas Andrews","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Andrews","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132804747","display_name":"Matthew Wiesner","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,United States","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5024403590"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87345584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6513000130653381,"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":0.6513000130653381,"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/T10863","display_name":"Voice and Speech Disorders","score":0.15060000121593475,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.11140000075101852,"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/stress","display_name":"Stress (linguistics)","score":0.6919000148773193},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5490000247955322},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4417000114917755},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.424699991941452},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.36160001158714294},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3447999954223633},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919000148773193},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6919000148773193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616100013256073},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41339999437332153},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.29499998688697815},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2849999964237213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332179","display_name":"Office of the Director","ror":"https://ror.org/04nseet23"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2295934277","https://openalex.org/W2888954148","https://openalex.org/W2972359262","https://openalex.org/W3097290232","https://openalex.org/W3198429080","https://openalex.org/W3209984917","https://openalex.org/W4319781852","https://openalex.org/W4319862272","https://openalex.org/W4367032484","https://openalex.org/W4372260574","https://openalex.org/W4385245566","https://openalex.org/W4385822302","https://openalex.org/W4385823180","https://openalex.org/W4385823191","https://openalex.org/W4385823392","https://openalex.org/W4385823432","https://openalex.org/W4386058698","https://openalex.org/W4391892546","https://openalex.org/W4393372125","https://openalex.org/W4401042974","https://openalex.org/W4402111470","https://openalex.org/W4402111633","https://openalex.org/W4402112533","https://openalex.org/W4402118925","https://openalex.org/W4402402635","https://openalex.org/W4403311272","https://openalex.org/W4406461669","https://openalex.org/W4408258404","https://openalex.org/W4408345715","https://openalex.org/W4408353806","https://openalex.org/W4415433047","https://openalex.org/W7148609082"],"related_works":[],"abstract_inverted_index":{"We":[0,53],"propose":[1],"a":[2,24],"method":[3],"to":[4,9,28,71,96,112],"scale":[5],"accented":[6,86,108],"TTS":[7,87,109],"training":[8],"large,":[10],"accent-diverse":[11],"datasets":[12],"that":[13,118],"often":[14],"lack":[15],"consistent,":[16],"high-quality":[17],"accent":[18,30,44,63,81,93,101,131],"labels.":[19],"Our":[20],"approach":[21,56],"relies":[22],"on":[23,57,76,99],"speech":[25,90],"geolocation":[26,120],"model":[27,88,121],"infer":[29],"labels":[31,64,102],"directly":[32],"from":[33,43,79],"audio.":[34],"To":[35],"improve":[36],"speaker":[37,42],"generalization":[38],"and":[39,125,130],"encourage":[40],"disentangling":[41],"we":[45],"explore":[46],"timbre":[47],"augmentation":[48,142],"through":[49],"kNN":[50],"voice":[51],"conversion.":[52],"validate":[54],"our":[55],"CommonVoice":[58],"by":[59],"fine-tuning":[60],"XTTS-v2":[61,97],"with":[62,91],"inferred":[65],"or":[66,105],"improved":[67,127],"via":[68],"geolocation.":[69],"According":[70,111],"various":[72],"automated":[73],"metrics":[74],"based":[75,122],"embeddings":[77],"extracted":[78],"an":[80],"identification":[82],"model,":[83],"the":[84,119,128,137],"resulting":[85],"produces":[89],"better":[92],"fidelity":[94,132],"compared":[95],"fine-tuned":[98],"self-reported":[100],"in":[103],"CommonVoice,":[104],"other":[106],"existing":[107],"models.":[110],"human":[113],"evaluation,":[114],"it":[115],"was":[116,144],"clear":[117],"data":[123,141],"discovery":[124],"enhancement":[126],"naturalness":[129],"of":[133,139],"generated":[134],"speech.":[135],"However,":[136],"effect":[138],"different":[140],"strategies":[143],"less":[145],"clear.":[146]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}