{"id":"https://openalex.org/W4372260139","doi":"https://doi.org/10.1109/icassp49357.2023.10095578","title":"Improving Speech-to-Speech Translation Through Unlabeled Text","display_name":"Improving Speech-to-Speech Translation Through Unlabeled Text","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260139","doi":"https://doi.org/10.1109/icassp49357.2023.10095578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095578","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041615748","display_name":"Xuan-Phi Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xuan-Phi Nguyen","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024195206","display_name":"Sravya Popuri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sravya Popuri","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhan Wang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052049405","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0003-2340-1109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110668","display_name":"Ilia Kulikov","orcid":"https://orcid.org/0000-0001-5989-9733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilia Kulikov","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103000746","display_name":"Hongyu Gong","orcid":"https://orcid.org/0000-0002-7071-0070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Gong","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5245,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84355302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"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":0.9991999864578247,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8333178758621216},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6553465723991394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6526159644126892},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6442790627479553},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6136375069618225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5971691012382507},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5770292282104492},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4689689874649048},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44023096561431885},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.43835899233818054},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.422634482383728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8333178758621216},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6553465723991394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6526159644126892},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6442790627479553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6136375069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5971691012382507},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5770292282104492},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4689689874649048},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44023096561431885},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.43835899233818054},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.422634482383728},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095578","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2097203679","https://openalex.org/W2136545725","https://openalex.org/W2144561273","https://openalex.org/W2219249508","https://openalex.org/W2889326796","https://openalex.org/W2914120296","https://openalex.org/W2946200149","https://openalex.org/W2964161387","https://openalex.org/W2972495969","https://openalex.org/W2989384871","https://openalex.org/W2989539713","https://openalex.org/W2995181338","https://openalex.org/W3001434439","https://openalex.org/W3015522062","https://openalex.org/W3015698636","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3036839309","https://openalex.org/W3054645415","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3119308075","https://openalex.org/W3127012371","https://openalex.org/W3140429000","https://openalex.org/W3169905056","https://openalex.org/W3180374548","https://openalex.org/W3197771105","https://openalex.org/W3198299542","https://openalex.org/W3209059054","https://openalex.org/W4287854499","https://openalex.org/W4296070387","https://openalex.org/W4385245566","https://openalex.org/W4394671563","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6767737316","https://openalex.org/W6770212971","https://openalex.org/W6771467084","https://openalex.org/W6779483622","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6781927165","https://openalex.org/W6785749098","https://openalex.org/W6790356757","https://openalex.org/W6796464841","https://openalex.org/W6798080464"],"related_works":["https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W1484029852","https://openalex.org/W4379525811","https://openalex.org/W2178499706","https://openalex.org/W3204668696","https://openalex.org/W3202905890","https://openalex.org/W2405158679","https://openalex.org/W4385570101","https://openalex.org/W4226543485"],"abstract_inverted_index":{"Direct":[0],"speech-to-speech":[1],"translation":[2,12,42,105],"(S2ST)":[3],"is":[4],"among":[5],"the":[6,11,16,29,64,90,98,101,114],"most":[7],"challenging":[8],"problems":[9],"in":[10,103,119],"paradigm":[13],"due":[14],"to":[15,27,54,62,72,80,89,108],"significant":[17],"scarcity":[18],"of":[19,77,100],"S2ST":[20,78,82],"data.":[21,93],"While":[22],"effort":[23],"has":[24,50],"been":[25],"made":[26],"increase":[28],"data":[30,79],"size":[31],"from":[32,69],"unlabeled":[33,48,67],"speech":[34,38],"by":[35,84,106,113],"cascading":[36],"pretrained":[37],"recognition":[39],"(ASR),":[40],"machine":[41],"(MT)":[43],"and":[44,126],"text-to-speech":[45],"(TTS)":[46],"models;":[47],"text":[49,68],"remained":[51],"relatively":[52],"under-utilized":[53],"improve":[55,81],"S2ST.":[56],"We":[57],"propose":[58],"an":[59],"effective":[60],"way":[61],"utilize":[63],"massive":[65],"existing":[66],"different":[70],"languages":[71],"create":[73],"a":[74],"large":[75],"amount":[76],"performance":[83],"applying":[85],"various":[86],"acoustic":[87],"effects":[88],"generated":[91],"synthetic":[92],"Empirically":[94],"our":[95],"method":[96,116],"outperforms":[97],"state":[99],"art":[102],"Spanish-English":[104,125],"up":[107],"2":[109],"BLEU.":[110],"Significant":[111],"gains":[112],"proposed":[115],"are":[117],"demonstrated":[118],"extremely":[120],"low-resource":[121],"settings":[122],"for":[123],"both":[124],"Russian-English":[127],"translations.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}