{"id":"https://openalex.org/W4408353156","doi":"https://doi.org/10.1109/icassp49660.2025.10888294","title":"Adversarial Speech-Text Pre-Training for Speech Translation","display_name":"Adversarial Speech-Text Pre-Training for Speech Translation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353156","doi":"https://doi.org/10.1109/icassp49660.2025.10888294"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5055075315","display_name":"Chenxuan Liu","orcid":"https://orcid.org/0009-0008-2704-9054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenxuan Liu","raw_affiliation_strings":["NERC-SLIP,USTC,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERC-SLIP,USTC,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430201","display_name":"Liping Chen","orcid":"https://orcid.org/0009-0003-6453-5645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liping Chen","raw_affiliation_strings":["NERC-SLIP,USTC,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERC-SLIP,USTC,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042203856","display_name":"Weitai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weitai Zhang","raw_affiliation_strings":["NERC-SLIP,USTC,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NERC-SLIP,USTC,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667935","display_name":"Xiaoxi Li","orcid":"https://orcid.org/0009-0003-0708-418X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxi Li","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027981943","display_name":"Peiwang Tang","orcid":"https://orcid.org/0000-0003-3681-0761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiwang Tang","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101662019","display_name":"Mingjia Yu","orcid":"https://orcid.org/0000-0002-8906-7476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingjia Yu","raw_affiliation_strings":["Coll. of Econ. & Mgmt.,CJLU,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coll. of Econ. & Mgmt.,CJLU,Hangzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,Dept. of Computer Science,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,Dept. of Computer Science,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087587703","display_name":"Zhongyi Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyi Ye","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.02601946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9746999740600586,"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":0.9746999740600586,"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":0.7879437804222107},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7633706331253052},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7141321897506714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6835182905197144},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6219396591186523},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5770753026008606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309455394744873},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5300436019897461},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4455922245979309},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.33920615911483765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879437804222107},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7633706331253052},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7141321897506714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6835182905197144},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6219396591186523},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5770753026008606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309455394744873},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5300436019897461},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4455922245979309},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.33920615911483765},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2466918907","https://openalex.org/W2605131327","https://openalex.org/W2766219058","https://openalex.org/W2963532001","https://openalex.org/W3007142233","https://openalex.org/W3011411500","https://openalex.org/W3037217258","https://openalex.org/W3092085609","https://openalex.org/W3113676066","https://openalex.org/W3176382501","https://openalex.org/W3202145349","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4223622550","https://openalex.org/W4385570522","https://openalex.org/W4392903148","https://openalex.org/W4392979802","https://openalex.org/W4402670331","https://openalex.org/W4404781855","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6781811055","https://openalex.org/W6796581206","https://openalex.org/W6803092890","https://openalex.org/W6810259195","https://openalex.org/W6839510803","https://openalex.org/W6847363464","https://openalex.org/W6852232343","https://openalex.org/W6870775139"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W1540615732","https://openalex.org/W4360995948"],"abstract_inverted_index":{"Large-scale":[0],"pre-training":[1,13,41],"has":[2],"been":[3],"shown":[4],"to":[5,25,133],"benefit":[6],"speech":[7,45,54,75,102,117,136,156],"translation":[8,137,157],"tasks.":[9],"However,":[10],"existing":[11],"multimodal":[12],"efforts":[14],"rely":[15],"on":[16,64,95,144],"parallel":[17,65,128],"corpora":[18],"for":[19,44],"semantic":[20,61,114],"alignment,":[21],"potentially":[22],"limiting":[23],"performance":[24,154],"the":[26,50,96,121,125,145,153],"scale":[27,126],"of":[28,53,59,127,155],"available":[29],"data":[30,33],"and":[31,55,76,82,103,108,138,159],"causing":[32],"imbalance.":[34],"Hence,":[35],"we":[36,68,87],"propose":[37],"an":[38,89],"adversarial":[39,90],"speech-text":[40],"(AST)":[42],"scheme":[43,48],"translation.":[46],"This":[47],"aligns":[49],"feature":[51,99],"distributions":[52,100],"text":[56,77],"modalities":[57,78],"instead":[58],"enforcing":[60],"alignment":[62],"based":[63],"corpora.":[66,129],"Specifically,":[67],"introduced":[69],"a":[70,106],"dual-stream":[71],"mechanism":[72],"that":[73,93,150],"bridges":[74],"through":[79],"speech,":[80],"text,":[81],"shared":[83],"encoders.":[84],"In":[85],"addition,":[86],"designed":[88],"bridging":[91],"method":[92],"focuses":[94],"differences":[97],"in":[98,116],"between":[101],"text.":[104],"Leveraging":[105],"discriminator":[107],"hidden":[109],"state-level":[110],"swapping":[111],"strategy":[112],"emphasizes":[113],"information":[115],"representations,":[118],"while":[119],"avoiding":[120],"limitations":[122],"imposed":[123],"by":[124],"We":[130],"applied":[131],"AST":[132,151],"both":[134],"end-to-end":[135],"large":[139,163],"model":[140],"architectures.":[141],"Experimental":[142],"results":[143],"IWSLT":[146],"test":[147],"sets":[148],"demonstrate":[149],"improved":[152],"models":[158],"is":[160],"compatible":[161],"with":[162],"language":[164],"models.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}