{"id":"https://openalex.org/W4392903174","doi":"https://doi.org/10.1109/icassp48485.2024.10447331","title":"TranSentence: speech-to-speech Translation via Language-Agnostic Sentence-Level Speech Encoding without Language-Parallel Data","display_name":"TranSentence: speech-to-speech Translation via Language-Agnostic Sentence-Level Speech Encoding without Language-Parallel Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903174","doi":"https://doi.org/10.1109/icassp48485.2024.10447331"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5007493723","display_name":"Seung-Bin Kim","orcid":"https://orcid.org/0000-0002-2287-9111"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seung-Bin Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320186","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-1477-6569"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2010Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea","Department of Artificial Intelligence, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007493723"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":1.022,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7869933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12722","last_page":"12726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.877859890460968},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.6548904180526733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6540117263793945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6072977185249329},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5382084846496582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5293080806732178},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5254482626914978},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.523044228553772},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.44423842430114746},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41773903369903564},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.32878783345222473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.877859890460968},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6548904180526733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6540117263793945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6072977185249329},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5382084846496582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293080806732178},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5254482626914978},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.523044228553772},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.44423842430114746},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41773903369903564},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.32878783345222473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1478288009","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2953128317","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G398188885","display_name":null,"funder_award_id":"2019-0-0007","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4643994530","display_name":null,"funder_award_id":"2021-0-02068","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7640390086","display_name":null,"funder_award_id":"019-0-00079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G8176700800","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8241800567","display_name":null,"funder_award_id":"2021-0-0206","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8436554242","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2097203679","https://openalex.org/W2136545725","https://openalex.org/W2972495969","https://openalex.org/W2997520586","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3140429000","https://openalex.org/W3180374548","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4287854499","https://openalex.org/W4372191700","https://openalex.org/W4372260088","https://openalex.org/W4372260139","https://openalex.org/W4372349107","https://openalex.org/W4378498579","https://openalex.org/W4385570550","https://openalex.org/W4385572318","https://openalex.org/W4392903062","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6810701745","https://openalex.org/W6838789019","https://openalex.org/W6841035593","https://openalex.org/W6852849868"],"related_works":["https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W2969905756","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W2772686614","https://openalex.org/W1489621819","https://openalex.org/W2572044271"],"abstract_inverted_index":{"Although":[0],"there":[1],"has":[2],"been":[3],"significant":[4],"advancement":[5],"in":[6,106],"the":[7,20,54,72,95,107,115],"field":[8],"of":[9,57,60],"speech-to-speech":[10,35,125],"translation,":[11],"conventional":[12],"models":[13],"still":[14],"require":[15],"language-parallel":[16,38],"speech":[17,39,50,69,80,105,112],"data":[18],"between":[19],"source":[21,116],"and":[22],"target":[23,96,103],"languages":[24],"for":[25],"training.":[26],"In":[27],"this":[28,89],"paper,":[29],"we":[30,44,100,120],"introduce":[31],"TranSentence,":[32],"a":[33,47,77],"novel":[34],"translation":[36],"without":[37],"data.":[40],"To":[41],"achieve":[42],"this,":[43],"first":[45],"adopt":[46],"language-agnostic":[48,78,111],"sentence-level":[49,79],"encoding":[51],"that":[52,82,131],"captures":[53],"semantic":[55],"information":[56],"speech,":[58],"irrespective":[59],"language.":[61],"We":[62],"then":[63],"train":[64],"our":[65],"model":[66],"to":[67,123,135],"generate":[68,102],"based":[70],"on":[71,94],"encoded":[73],"embedding":[74,113],"obtained":[75],"from":[76,114],"encoder":[81],"is":[83,133],"pre-trained":[84],"with":[85],"various":[86],"languages.":[87],"With":[88],"method,":[90],"despite":[91],"training":[92],"exclusively":[93],"language\u2019s":[97],"monolingual":[98],"data,":[99],"can":[101],"language":[104,117],"inference":[108],"stage":[109],"using":[110],"speech.":[118],"Furthermore,":[119],"extend":[121],"TranSentence":[122,132],"multilingual":[124],"translation.":[126],"The":[127],"experimental":[128],"results":[129],"demonstrate":[130],"superior":[134],"other":[136],"models.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}