{"id":"https://openalex.org/W4386590854","doi":"https://doi.org/10.1109/lsp.2023.3313513","title":"Direct Text to Speech Translation System Using Acoustic Units","display_name":"Direct Text to Speech Translation System Using Acoustic Units","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386590854","doi":"https://doi.org/10.1109/lsp.2023.3313513"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3313513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3313513","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.07478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053658389","display_name":"Victoria Mingote","orcid":"https://orcid.org/0000-0002-3505-0249"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Victoria Mingote","raw_affiliation_strings":["ViVoLab - Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3505-0249","affiliations":[{"raw_affiliation_string":"ViVoLab - Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069847313","display_name":"Pablo Gimeno","orcid":"https://orcid.org/0000-0002-3142-0708"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Gimeno","raw_affiliation_strings":["ViVoLab - Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3142-0708","affiliations":[{"raw_affiliation_string":"ViVoLab - Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645455","display_name":"Luis Vicente","orcid":"https://orcid.org/0000-0003-4391-5203"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Vicente","raw_affiliation_strings":["ViVoLab - Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0003-4391-5203","affiliations":[{"raw_affiliation_string":"ViVoLab - Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035187454","display_name":"Sameer Khurana","orcid":"https://orcid.org/0000-0002-3182-1085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sameer Khurana","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3182-1085","affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["LIUM, Le Mans University, Le Mans, France"],"raw_orcid":"https://orcid.org/0000-0002-2653-1008","affiliations":[{"raw_affiliation_string":"LIUM, Le Mans University, Le Mans, France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009747333","display_name":"Jarod Duret","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jarod Duret","raw_affiliation_strings":["LIA, Avignon University, Avignon, France"],"raw_orcid":"https://orcid.org/0000-0002-5755-2653","affiliations":[{"raw_affiliation_string":"LIA, Avignon University, Avignon, France","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053658389"],"corresponding_institution_ids":["https://openalex.org/I255234318"],"apc_list":null,"apc_paid":null,"fwci":1.6567,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87205999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1262","last_page":"1266"},"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.899339497089386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8577776551246643},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7300699949264526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.719202995300293},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5580614805221558},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5370347499847412},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5304968357086182},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5067675709724426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5049625039100647},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.47180333733558655},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.446164071559906},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4340737760066986},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4180399477481842},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4174674451351166},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.40724867582321167},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0691537857055664}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.899339497089386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8577776551246643},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7300699949264526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.719202995300293},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5580614805221558},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5370347499847412},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5304968357086182},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5067675709724426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049625039100647},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.47180333733558655},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.446164071559906},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4340737760066986},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4180399477481842},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4174674451351166},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.40724867582321167},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0691537857055664},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2023.3313513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3313513","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2309.07478","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07478","pdf_url":"https://arxiv.org/pdf/2309.07478","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.07478","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07478","pdf_url":"https://arxiv.org/pdf/2309.07478","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G1454328438","display_name":null,"funder_award_id":"101007666","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7532365945","display_name":null,"funder_award_id":"PDC2021-120846-C41","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324111","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386590854.pdf","grobid_xml":"https://content.openalex.org/works/W4386590854.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2933138175","https://openalex.org/W2964243274","https://openalex.org/W2972495969","https://openalex.org/W3001434439","https://openalex.org/W3092028330","https://openalex.org/W3107826490","https://openalex.org/W3119308075","https://openalex.org/W3140429000","https://openalex.org/W3160525311","https://openalex.org/W3160799772","https://openalex.org/W3169320628","https://openalex.org/W3169483174","https://openalex.org/W3173767661","https://openalex.org/W3180374548","https://openalex.org/W3209059054","https://openalex.org/W3213018012","https://openalex.org/W3213029956","https://openalex.org/W4221155340","https://openalex.org/W4226444650","https://openalex.org/W4286359908","https://openalex.org/W4287072252","https://openalex.org/W4287854499","https://openalex.org/W4367841185","https://openalex.org/W4375869259","https://openalex.org/W4394671563","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6803675045","https://openalex.org/W6810259195","https://openalex.org/W6810701745","https://openalex.org/W6841035593"],"related_works":["https://openalex.org/W4385571610","https://openalex.org/W2969905756","https://openalex.org/W4200068392","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W2772686614","https://openalex.org/W2293738010","https://openalex.org/W2036933852","https://openalex.org/W2251328660","https://openalex.org/W2105439218"],"abstract_inverted_index":{"This":[0,14],"paper":[1],"proposes":[2],"a":[3,68,73,89,135,144],"direct":[4,51,98],"text":[5,17,35,99,113],"to":[6,24,53,62,85,100],"speech":[7,26,52,54,69,92,101],"translation":[8,55,102],"system":[9],"using":[10,67],"discrete":[11],"acoustic":[12,45,65],"units.":[13,94],"framework":[15],"employs":[16],"in":[18,27,37,47],"different":[19,112],"source":[20],"languages":[21],"as":[22,117],"input":[23],"generate":[25],"the":[28,32,42,59,64,106,128],"target":[29],"language":[30,129],"without":[31],"need":[33],"for":[34,50,97,125],"transcriptions":[36],"this":[38],"language.":[39],"Motivated":[40],"by":[41],"success":[43],"of":[44,127],"units":[46,66,77],"previous":[48],"works":[49],"systems,":[56],"we":[57],"use":[58],"same":[60],"pipeline":[61],"extract":[63],"encoder":[70],"combined":[71],"with":[72,110,143,147],"clustering":[74],"algorithm.":[75],"Once":[76],"are":[78],"obtained,":[79],"an":[80],"encoder-decoder":[81],"architecture":[82,142],"is":[83],"trained":[84],"predict":[86],"them.":[87],"Then":[88],"vocoder":[90],"generates":[91],"from":[93],"Our":[95],"approach":[96],"was":[103],"tested":[104],"on":[105],"new":[107],"CVSS":[108],"corpus":[109],"two":[111],"mBART":[114],"models":[115],"employed":[116],"initialisation.":[118],"The":[119],"systems":[120],"presented":[121],"report":[122],"competitive":[123],"performance":[124],"most":[126],"pairs":[130],"evaluated.":[131],"Besides,":[132],"results":[133],"show":[134],"remarkable":[136],"improvement":[137],"when":[138],"initialising":[139],"our":[140],"proposed":[141],"model":[145],"pre-trained":[146],"more":[148],"languages.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}