{"id":"https://openalex.org/W7082659582","doi":"https://doi.org/10.3724/2096-7004.di.2025.0135","title":"PhoenixS: Enhanced Self-reconstruction with Pre-trained Decoder for Speech-to-Speech Translation Using Monolingual Data","display_name":"PhoenixS: Enhanced Self-reconstruction with Pre-trained Decoder for Speech-to-Speech Translation Using Monolingual Data","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W7082659582","doi":"https://doi.org/10.3724/2096-7004.di.2025.0135"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0135","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0135","pdf_url":null,"source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.3724/2096-7004.di.2025.0135","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei Zong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Zong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaona Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaona Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Haizhou Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55557534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250135","last_page":"20250135"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13655","display_name":"Canadian Policy and Governance","score":0.12430000305175781,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13655","display_name":"Canadian Policy and Governance","score":0.12430000305175781,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13148","display_name":"Environmental and Air Quality Management","score":0.026200000196695328,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13546","display_name":"Census and Population Estimation","score":0.01899999938905239,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6233000159263611},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6161999702453613},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5701000094413757},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.526199996471405},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4943999946117401},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4900999963283539},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4108000099658966},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485000133514404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6284000277519226},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6233000159263611},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6161999702453613},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120000243186951},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4943999946117401},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.387800008058548},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0135","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0135","pdf_url":null,"source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0135","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0135","pdf_url":null,"source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.552412211894989,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Direct":[0],"speech-to-speech":[1],"translation":[2,53,83],"(S2ST)":[3],"has":[4],"gained":[5],"increasing":[6],"attention":[7],"in":[8,42,86],"recent":[9],"years":[10],"due":[11],"to":[12,51,67],"its":[13],"advantages":[14],"over":[15],"cascade":[16],"models.":[17],"However,":[18],"it":[19],"still":[20],"suffers":[21],"from":[22],"the":[23,30,82,91,115,120],"challenge":[24],"of":[25,29,33,61,112],"data":[26,56],"scarcity":[27],"because":[28],"limited":[31],"availability":[32],"parallel":[34],"bilingual":[35],"speech":[36,50,52,65,74],"data.":[37],"To":[38,80],"address":[39],"this":[40,43],"issue,":[41],"paper,":[44],"we":[45,89],"propose":[46],"PhoenixS,":[47],"which":[48,95],"achieves":[49,108],"with":[54,100],"monolingual":[55],"only.":[57],"We":[58],"take":[59],"advantage":[60],"a":[62,76],"universal":[63],"language-agnostic":[64],"encoder":[66],"encode":[68],"both":[69],"source":[70],"and":[71],"target":[72],"language":[73],"into":[75],"shared":[77],"embedding":[78],"space.":[79],"enhance":[81],"performance,":[84],"especially":[85],"low-resource":[87],"settings,":[88],"introduce":[90],"pre-trained":[92],"unit-mBART":[93],"decoder,":[94],"can":[96],"be":[97],"further":[98],"combined":[99],"speech-denoising":[101],"techniques.":[102],"Our":[103],"experiments":[104],"show":[105],"that":[106],"PhoenixS":[107],"an":[109],"average":[110],"BLEU":[111],"26.35":[113],"on":[114],"CVSS-C":[116],"Es-En":[117],"corpus,":[118],"outperforming":[119],"previous":[121],"best":[122],"method":[123],"by":[124],"5.25":[125],"BLEU.":[126],"Audio":[127],"samples":[128],"are":[129],"available":[130],"at":[131],"<uri":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"":[133],"xlink:href=\"https://zenniq.github.io/PhoenixS_page/\">https://zenniq.github.io/PhoenixS_page/</uri>.":[134]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}