{"id":"https://openalex.org/W4406461669","doi":"https://doi.org/10.1109/slt61566.2024.10832155","title":"Cross-Dialect Text-to-Speech In Pitch-Accent Language Incorporating Multi-Dialect Phoneme-Level Bert","display_name":"Cross-Dialect Text-to-Speech In Pitch-Accent Language Incorporating Multi-Dialect Phoneme-Level Bert","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461669","doi":"https://doi.org/10.1109/slt61566.2024.10832155"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5108574971","display_name":"Kazuki Yamauchi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kazuki Yamauchi","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042731264","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-4825-7783"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108574971"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.9481,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8119247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"750","last_page":"757"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9973000288009644,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.7252662181854248},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.7029978036880493},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6353386640548706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6030272245407104},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.460475355386734},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4183163046836853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3795713186264038},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.18314006924629211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252662181854248},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.7029978036880493},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6353386640548706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6030272245407104},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.460475355386734},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4183163046836853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3795713186264038},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.18314006924629211},{"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/slt61566.2024.10832155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338246","display_name":"ACT-X","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W2115040572","https://openalex.org/W2471520273","https://openalex.org/W2752796333","https://openalex.org/W2890964092","https://openalex.org/W2964138190","https://openalex.org/W2973158936","https://openalex.org/W3081800019","https://openalex.org/W3096514088","https://openalex.org/W3161436426","https://openalex.org/W3193689627","https://openalex.org/W3197324626","https://openalex.org/W4285412695","https://openalex.org/W4296068758","https://openalex.org/W4312095991","https://openalex.org/W4372267432","https://openalex.org/W4384918448","https://openalex.org/W4391827315","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6749555683","https://openalex.org/W6752467913","https://openalex.org/W6761205521","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6847363464","https://openalex.org/W6854866820","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W2072461533","https://openalex.org/W162378616","https://openalex.org/W4251666207","https://openalex.org/W2087397317"],"abstract_inverted_index":{"We":[0],"explore":[1],"cross-dialect":[2],"text-to-speech(CD-TTS),a":[3],"task":[4],"to":[5,36,48,72,76],"synthesize":[6,49],"learned":[7],"speakers\u2019voices":[8],"in":[9,12,124],"non-native":[10],"dialects,especially":[11],"pitch-accent":[13],"languages.CD-TTS":[14],"is":[15],"important":[16],"for":[17],"developing":[18],"voice":[19],"agents":[20],"that":[21,114],"naturally":[22],"communicate":[23],"with":[24,103],"people":[25],"across":[26],"regions.We":[27],"present":[28],"a":[29,44,53,64,77,104],"novel":[30,85],"TTS":[31,46,91,110],"model":[32,47,99,116],"comprising":[33],"three":[34],"sub-modules":[35],"perform":[37],"competitively":[38],"at":[39],"this":[40],"task.We":[41],"first":[42],"train":[43,68],"backbone":[45],"dialect":[50,79,109],"speech":[51,62,123],"from":[52,61,80,107],"text":[54,82],"conditioned":[55],"on":[56],"phoneme-level":[57,87],"accent":[58],"latent":[59],"variables(ALVs)extracted":[60],"by":[63,100],"reference":[65],"encoder.":[66],"Then,we":[67],"an":[69],"ALV":[70],"predictor":[71],"predict":[73],"ALVs":[74],"tailored":[75],"target":[78],"input":[81],"leveraging":[83],"our":[84,98,115],"multi-dialect":[86,90],"BERT.We":[88],"conduct":[89],"experiments":[92],"and":[93],"evaluate":[94],"the":[95,118],"effectiveness":[96],"of":[97,121],"comparing":[101],"it":[102],"baseline":[105],"derived":[106],"conventional":[108],"methods.The":[111],"results":[112],"show":[113],"improves":[117],"dialectal":[119],"naturalness":[120],"synthetic":[122],"CD-TTS.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}