{"id":"https://openalex.org/W4406163711","doi":"https://doi.org/10.1109/access.2025.3527012","title":"ZeST: A Zero-Resourced Speech-to-Speech Translation Approach for Unknown, Unpaired, and Untranscribed Languages","display_name":"ZeST: A Zero-Resourced Speech-to-Speech Translation Approach for Unknown, Unpaired, and Untranscribed Languages","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406163711","doi":"https://doi.org/10.1109/access.2025.3527012"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3527012","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3527012","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3527012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101535040","display_name":"Luan Thanh Nguyen","orcid":"https://orcid.org/0000-0003-4882-8336"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Luan Thanh Nguyen","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101535040"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8911344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"8638","last_page":"8648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9840999841690063,"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":0.9840999841690063,"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":0.953499972820282,"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/T10028","display_name":"Topic Modeling","score":0.928600013256073,"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/zest","display_name":"Zest","score":0.8317615985870361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7051166296005249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6577924489974976},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6367491483688354},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5286182761192322},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4699818193912506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3763314485549927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3572727143764496},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.21222227811813354},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19930416345596313},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.137131005525589}],"concepts":[{"id":"https://openalex.org/C2778051730","wikidata":"https://www.wikidata.org/wiki/Q8069690","display_name":"Zest","level":2,"score":0.8317615985870361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7051166296005249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6577924489974976},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6367491483688354},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5286182761192322},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4699818193912506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3763314485549927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3572727143764496},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.21222227811813354},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19930416345596313},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.137131005525589},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3527012","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3527012","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4da6a95e484428b8165a874876c720e","is_oa":true,"landing_page_url":"https://doaj.org/article/c4da6a95e484428b8165a874876c720e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 8638-8648 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3527012","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3527012","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1435354637","display_name":null,"funder_award_id":"JP23K21681","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1861492603","https://openalex.org/W1902237438","https://openalex.org/W1975781079","https://openalex.org/W2101105183","https://openalex.org/W2483512167","https://openalex.org/W2586148577","https://openalex.org/W2842511635","https://openalex.org/W2919290281","https://openalex.org/W2920166246","https://openalex.org/W2962784628","https://openalex.org/W2963330681","https://openalex.org/W2964001192","https://openalex.org/W2964243274","https://openalex.org/W2982083293","https://openalex.org/W3034625919","https://openalex.org/W3119308075","https://openalex.org/W3142316150","https://openalex.org/W3157861865","https://openalex.org/W3159481202","https://openalex.org/W3174311593","https://openalex.org/W3180374548","https://openalex.org/W3209059054","https://openalex.org/W4205480693","https://openalex.org/W4221153524","https://openalex.org/W4224875474","https://openalex.org/W4287854499","https://openalex.org/W4296070387","https://openalex.org/W4372266917","https://openalex.org/W4381786045","https://openalex.org/W4388072808","https://openalex.org/W4401607735","https://openalex.org/W4402111993","https://openalex.org/W4404781583","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6727690538","https://openalex.org/W6729977899","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6781811055","https://openalex.org/W6790356757"],"related_works":["https://openalex.org/W1976564100","https://openalex.org/W2033546287","https://openalex.org/W4313317310","https://openalex.org/W2000069757","https://openalex.org/W193772402","https://openalex.org/W3097368179","https://openalex.org/W4385272979","https://openalex.org/W2314398467","https://openalex.org/W2903247141","https://openalex.org/W123774389"],"abstract_inverted_index":{"Speech-to-speech":[0],"translation":[1,15,57,97,124],"(S2ST)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,51],"practical":[7],"solution":[8],"for":[9,35,98],"overcoming":[10],"linguistic":[11],"barriers,":[12],"enabling":[13],"direct":[14,122],"between":[16],"spoken":[17],"languages":[18,100],"without":[19,125],"relying":[20,126],"on":[21,127],"intermediate":[22],"text":[23],"representations.":[24],"However,":[25],"existing":[26],"S2ST":[27],"systems":[28],"face":[29],"significant":[30],"challenges,":[31],"including":[32],"the":[33,41,60,117,137,144],"requirement":[34],"extensive":[36],"parallel":[37,131],"speech":[38,79,89,103,148],"data":[39,83,113,129],"and":[40,66,92,105,150],"limitations":[42],"of":[43,62,71,139,146],"known":[44],"written":[45],"languages.":[46,68],"This":[47],"paper":[48],"proposes":[49],"ZeST,":[50],"novel":[52],"zero-resourced":[53,147],"approach":[54],"to":[55,143],"speech-to-speech":[56,96,123],"that":[58,116],"addresses":[59],"challenges":[61],"processing":[63,149],"unknown,":[64],"unpaired,":[65],"untranscribed":[67,99],"ZeST":[69,118,140],"consists":[70],"two":[72],"main":[73],"phases:":[74],"(1)":[75],"Discovering":[76],"semantically":[77],"related":[78],"pairs":[80],"from":[81],"unpaired":[82],"by":[84],"leveraging":[85],"self-supervised":[86],"visually":[87],"grounded":[88],"(VGS)":[90],"models":[91],"(2)":[93],"Achieving":[94],"textless":[95],"using":[101,110],"discrete":[102],"representations":[104],"sequence-to-sequence":[106],"modeling.":[107],"Experimental":[108],"evaluations":[109],"three":[111],"different":[112],"scenarios":[114],"demonstrate":[115],"system":[119],"effectively":[120],"performs":[121],"transcribed":[128],"or":[130],"corpora.":[132],"The":[133],"experimental":[134],"results":[135],"highlight":[136],"potential":[138],"in":[141,153],"contributing":[142],"field":[145],"improving":[151],"communication":[152],"multilingual":[154],"societies.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
