{"id":"https://openalex.org/W4402993510","doi":"https://doi.org/10.3233/faia240427","title":"Speech Synthesis of Valencian Using a Conditional Variational Autoencoder with Adversarial Learning","display_name":"Speech Synthesis of Valencian Using a Conditional Variational Autoencoder with Adversarial Learning","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4402993510","doi":"https://doi.org/10.3233/faia240427"},"language":"en","primary_location":{"id":"doi:10.3233/faia240427","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240427","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107666171","display_name":"Joan Arag\u00f3","orcid":null},"institutions":[{"id":"https://openalex.org/I47652572","display_name":"La Salle University","ror":"https://ror.org/02beve479","country_code":"US","type":"education","lineage":["https://openalex.org/I47652572"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joan Arag\u00f3","raw_affiliation_strings":["La Salle - URL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"La Salle - URL","institution_ids":["https://openalex.org/I47652572"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032719854","display_name":"Marc Freixes","orcid":"https://orcid.org/0000-0001-9363-9513"},"institutions":[{"id":"https://openalex.org/I47652572","display_name":"La Salle University","ror":"https://ror.org/02beve479","country_code":"US","type":"education","lineage":["https://openalex.org/I47652572"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Freixes","raw_affiliation_strings":["La Salle - URL"],"raw_orcid":"https://orcid.org/0000-0001-9363-9513","affiliations":[{"raw_affiliation_string":"La Salle - URL","institution_ids":["https://openalex.org/I47652572"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107666171"],"corresponding_institution_ids":["https://openalex.org/I47652572"],"apc_list":null,"apc_paid":null,"fwci":0.749,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73479406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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":0.9944000244140625,"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/T10860","display_name":"Speech and Audio Processing","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9117000102996826,"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/autoencoder","display_name":"Autoencoder","score":0.8792325258255005},{"id":"https://openalex.org/keywords/valencian","display_name":"Valencian","score":0.712531328201294},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5471859574317932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5058310031890869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48988407850265503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48605138063430786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36973369121551514},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32349470257759094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2131677269935608},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19153949618339539},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08023610711097717}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8792325258255005},{"id":"https://openalex.org/C2775847123","wikidata":"https://www.wikidata.org/wiki/Q32641","display_name":"Valencian","level":2,"score":0.712531328201294},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5471859574317932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5058310031890869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48988407850265503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48605138063430786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36973369121551514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32349470257759094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2131677269935608},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19153949618339539},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08023610711097717}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia240427","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240427","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:dau.url.edu:20.500.14342/6074","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.14342/6074","pdf_url":"https://dau.url.edu/bitstream/20.500.14342/6074/1/FAIA-390-FAIA240427.pdf","source":{"id":"https://openalex.org/S7407055114","display_name":"DAU - Digital Archive of URL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3233/faia240427","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240427","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2244991559","https://openalex.org/W2530133537","https://openalex.org/W2639537841","https://openalex.org/W2011679619","https://openalex.org/W4313442036","https://openalex.org/W2507594196","https://openalex.org/W2127127192","https://openalex.org/W1573576781","https://openalex.org/W2112716978","https://openalex.org/W3013693939"],"abstract_inverted_index":{"The":[0],"growing":[1],"demand":[2],"for":[3,15,32,67,139],"high-quality":[4],"speech":[5,25,44,93,143],"synthesis":[6,135,144],"systems":[7,145],"in":[8,118,146],"minority":[9,148],"languages":[10],"presents":[11],"a":[12,50,54,72],"notable":[13],"challenge":[14],"researchers.":[16],"In":[17],"response,":[18],"this":[19,33],"study":[20],"focuses":[21],"on":[22,53],"synthesizing":[23],"Valencian":[24,109,123,133],"to":[26,48,89,105,128],"develop":[27],"an":[28],"effective":[29],"text-to-speech":[30,134],"system":[31],"linguistic":[34],"variety.":[35],"A":[36],"meticulously":[37],"recorded":[38],"corpus,":[39],"comprising":[40],"7":[41],"hours":[42],"of":[43,132,142],"data,":[45],"was":[46,76,87],"utilised":[47],"train":[49],"model":[51,75,101,110],"based":[52],"conditional":[55],"variational":[56],"autoencoder":[57],"with":[58,64],"adversarial":[59,65],"learning,":[60],"specifically":[61],"Variational":[62],"Inference":[63],"learning":[66],"end-to-end":[68],"Text-to-Speech":[69],"(VITS).":[70],"Additionally,":[71],"pretrained":[73],"multispeaker":[74],"fine-tuned":[77],"using":[78],"30":[79],"minutes,":[80],"and":[81,121,136],"the":[82,91,99,106,112,130,140],"entire":[83],"corpus.":[84],"Perceptual":[85],"testing":[86],"conducted":[88],"evaluate":[90],"synthesised":[92],"quality,":[94],"revealing":[95],"promising":[96],"results.":[97],"Notably,":[98],"proposed":[100],"demonstrated":[102],"competitiveness":[103],"compared":[104],"recently":[107],"released":[108],"by":[111],"Aina":[113],"project,":[114],"indicating":[115],"its":[116],"efficacy":[117],"generating":[119],"natural":[120],"fluent":[122],"speech.":[124],"These":[125],"findings":[126],"contribute":[127],"advancing":[129],"field":[131],"carry":[137],"implications":[138],"development":[141],"other":[147],"languages.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
