{"id":"https://openalex.org/W4408355685","doi":"https://doi.org/10.1109/icassp49660.2025.10889325","title":"Large Language Models Are Efficient Learners as Zero-Shot Speech Translators","display_name":"Large Language Models Are Efficient Learners as Zero-Shot Speech Translators","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355685","doi":"https://doi.org/10.1109/icassp49660.2025.10889325"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889325","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":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxuan Liu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430194","display_name":"Liping Chen","orcid":"https://orcid.org/0000-0002-9421-1049"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Chen","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"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/A5042203856","display_name":"Weitai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitai Zhang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"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/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,College Park,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087587703","display_name":"Zhongyi Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyi Ye","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101662019","display_name":"Mingjia Yu","orcid":"https://orcid.org/0000-0002-8906-7476"},"institutions":[{"id":"https://openalex.org/I55538621","display_name":"China Jiliang University","ror":"https://ror.org/05v1y0t93","country_code":"CN","type":"education","lineage":["https://openalex.org/I55538621"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjia Yu","raw_affiliation_strings":["China Jiliang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Jiliang University,Hangzhou,China","institution_ids":["https://openalex.org/I55538621"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3536,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90416063,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"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":0.9592000246047974,"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":0.9592000246047974,"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":0.9577000141143799,"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":0.7565770149230957},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6905688643455505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4738110601902008},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.443426251411438},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.43243926763534546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4122200310230255},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26188522577285767}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565770149230957},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6905688643455505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4738110601902008},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.443426251411438},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.43243926763534546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4122200310230255},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26188522577285767},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889325","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2466918907","https://openalex.org/W2605131327","https://openalex.org/W3196509775","https://openalex.org/W3209984917","https://openalex.org/W4285077564","https://openalex.org/W4319862635","https://openalex.org/W4391021773","https://openalex.org/W4392903148","https://openalex.org/W4392931630","https://openalex.org/W4393160302","https://openalex.org/W4401996408","https://openalex.org/W4402667113","https://openalex.org/W4402671980","https://openalex.org/W4402684152","https://openalex.org/W6778883912","https://openalex.org/W6800751262","https://openalex.org/W6800875267","https://openalex.org/W6810738896","https://openalex.org/W6845413636","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6852909395","https://openalex.org/W6853465110","https://openalex.org/W6854445763","https://openalex.org/W6856881632","https://openalex.org/W6857131320","https://openalex.org/W6858893317","https://openalex.org/W6860465438","https://openalex.org/W6860809563","https://openalex.org/W6861152725","https://openalex.org/W6861190020","https://openalex.org/W6869522536"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Significant":[0],"progress":[1],"has":[2],"recently":[3],"been":[4],"made":[5],"in":[6,73],"combining":[7],"Speech":[8,57],"Foundation":[9],"Models":[10,15],"(SFMs)":[11],"and":[12,71,95,116,126,131,148],"Large":[13],"Language":[14],"(LLMs)":[16],"into":[17,63],"a":[18,74],"unified":[19],"model":[20,99],"to":[21,30,32,51,150],"tackle":[22],"Speech-to-Text":[23],"Translation":[24,87],"(ST)":[25],"tasks.":[26],"However,":[27],"fine-tuning":[28,78],"LLMs":[29,50,72],"adapt":[31],"specific":[33],"downstream":[34,151],"tasks":[35,153],"requires":[36],"substantial":[37],"resources,":[38],"which":[39,91],"is":[40],"often":[41],"infeasible.":[42],"Therefore,":[43],"this":[44],"study":[45],"proposes":[46],"using":[47],"Chain-of-Thought":[48],"(CoT)-based":[49],"perform":[52],"error":[53,108],"correction":[54],"on":[55],"Automatic":[56],"Recognition":[58],"results":[59,138],"followed":[60],"by":[61],"translation":[62,119],"the":[64,98,111,129,134,141],"target":[65],"language.":[66],"This":[67],"approach":[68,143],"combines":[69],"SFMs":[70],"lightweight":[75],"manner":[76],"without":[77],"or":[79],"large":[80],"parallel":[81],"corpora.":[82],"Additionally,":[83],"through":[84],"our":[85],"proposed":[86,135,142],"Graph":[88],"CoT":[89,113],"(TGCoT),":[90],"involves":[92],"iterative":[93],"feedback":[94],"Back":[96],"Translation,":[97],"can":[100],"self-check":[101],"when":[102],"errors":[103],"are":[104],"detected,":[105],"effectively":[106],"reducing":[107],"accumulation":[109],"during":[110],"multi-step":[112],"reasoning":[114],"process":[115],"thereby":[117],"improving":[118],"accuracy.":[120],"Finally,":[121],"extensive":[122],"experiments":[123],"across":[124],"languages":[125],"models":[127],"demonstrate":[128],"superiority":[130],"robustness":[132],"of":[133],"method.":[136],"The":[137],"show":[139],"that":[140],"better":[144],"unleashes":[145],"LLM":[146],"capabilities":[147],"adapts":[149],"ST":[152],"with":[154],"minimal":[155],"resources.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}