{"id":"https://openalex.org/W4384702663","doi":"https://doi.org/10.1109/iwssip58668.2023.10180259","title":"Cross-lingual Text-to-Speech with Prosody Embedding","display_name":"Cross-lingual Text-to-Speech with Prosody Embedding","publication_year":2023,"publication_date":"2023-06-27","ids":{"openalex":"https://openalex.org/W4384702663","doi":"https://doi.org/10.1109/iwssip58668.2023.10180259"},"language":"en","primary_location":{"id":"doi:10.1109/iwssip58668.2023.10180259","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iwssip58668.2023.10180259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)","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/A5055197467","display_name":"Tijana Nosek","orcid":"https://orcid.org/0000-0002-3707-0286"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Tijana Nosek","raw_affiliation_strings":["University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","institution_ids":["https://openalex.org/I170726198"]},{"raw_affiliation_string":"Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053625267","display_name":"Sini\u0161a Suzi\u0107","orcid":"https://orcid.org/0000-0002-0511-6729"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Sini\u0161a Suzi\u0107","raw_affiliation_strings":["University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","institution_ids":["https://openalex.org/I170726198"]},{"raw_affiliation_string":"Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074165790","display_name":"Vlado Deli\u0107","orcid":"https://orcid.org/0000-0002-4558-9918"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Vlado Deli\u0107","raw_affiliation_strings":["University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","institution_ids":["https://openalex.org/I170726198"]},{"raw_affiliation_string":"Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085575169","display_name":"Milan Se\u010dujski","orcid":"https://orcid.org/0000-0002-3426-3277"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Milan Se\u010dujski","raw_affiliation_strings":["University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Novi Sad,Faculty of Technical Sciences,Novi Sad,Serbia","institution_ids":["https://openalex.org/I170726198"]},{"raw_affiliation_string":"Faculty of Technical Sciences, University of Novi Sad, Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170726198"],"apc_list":null,"apc_paid":null,"fwci":0.3226,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63914796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"i","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/T10181","display_name":"Natural Language Processing Techniques","score":0.994700014591217,"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":0.9937000274658203,"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":0.8316068649291992},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7143614888191223},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6511964797973633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6061189770698547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.597492516040802},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.5466034412384033},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5370228886604309},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5151265859603882},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5034834742546082},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4948078989982605},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.49255356192588806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48620954155921936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8316068649291992},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7143614888191223},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6511964797973633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6061189770698547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.597492516040802},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.5466034412384033},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5370228886604309},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5151265859603882},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5034834742546082},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4948078989982605},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.49255356192588806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48620954155921936},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwssip58668.2023.10180259","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iwssip58668.2023.10180259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320329307","display_name":"Science Fund of the Republic of Serbia","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W36870606","https://openalex.org/W88751538","https://openalex.org/W113498433","https://openalex.org/W123943236","https://openalex.org/W2025638820","https://openalex.org/W2114010348","https://openalex.org/W2123808477","https://openalex.org/W2401698713","https://openalex.org/W2471520273","https://openalex.org/W2507912506","https://openalex.org/W2598638573","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2973084242","https://openalex.org/W3034949308","https://openalex.org/W3150572638","https://openalex.org/W3216873902","https://openalex.org/W4224917388","https://openalex.org/W4226424742","https://openalex.org/W4372260365","https://openalex.org/W6601527497","https://openalex.org/W6725315082","https://openalex.org/W6811227718"],"related_works":["https://openalex.org/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2465421051","https://openalex.org/W1984347656","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W2772686614","https://openalex.org/W4200068392","https://openalex.org/W2036933852"],"abstract_inverted_index":{"The":[0,36,117],"research":[1],"presented":[2],"in":[3,39,91,99,149],"the":[4,7,20,33,40,47,80,100,109,145,159],"paper":[5,41],"handles":[6],"problem":[8],"of":[9,15,17,23,49,70,102,125,132,137,147,161],"multilingual":[10],"text-to-speech,":[11],"particularly":[12],"its":[13],"capability":[14],"synthesis":[16,45,138,148],"speech":[18,44,98,123],"when":[19],"appropriate":[21],"combination":[22],"desired":[24],"properties":[25],"(speaker,":[26],"language,":[27],"speaking":[28,59],"style)":[29],"is":[30],"missing":[31],"from":[32],"training":[34],"corpus.":[35],"model":[37,81,119],"proposed":[38,118],"achieves":[42],"cross-lingual":[43,165],"through":[46],"use":[48],"neural":[50],"network":[51],"embeddings,":[52],"applied":[53],"not":[54],"only":[55],"to":[56,64,82,96,142],"speaker":[57,162],"and":[58,67,75,88,94,128,152,166],"style":[60],"IDs,":[61],"but":[62],"also":[63],"context-dependent":[65],"phonemes":[66],"a":[68,103,114],"range":[69,131],"prosodic":[71,89],"events,":[72],"including":[73,134],"accents":[74],"phrase":[76],"breaks.":[77],"This":[78],"allows":[79],"efficiently":[83],"capture":[84],"relationships":[85],"between":[86,164],"phones":[87],"events":[90],"different":[92,150,154],"languages,":[93],"consequently":[95],"synthesize":[97],"voice":[101],"person":[104],"who":[105],"has":[106],"never":[107],"spoken":[108],"target":[110,115],"language":[111,168],"or":[112],"used":[113],"style.":[116],"was":[120,139],"trained":[121],"on":[122],"corpora":[124],"American":[126],"English":[127],"Serbo-Croatian.":[129],"A":[130],"experiments":[133],"subjective":[135],"evaluation":[136],"carried":[140],"out":[141],"establish":[143],"both":[144],"quality":[146],"scenarios":[151],"under":[153],"conditions,":[155],"as":[156,158],"well":[157],"similarity":[160],"voices":[163],"original":[167],"scenario.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
